Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is clear. The description adds valuable behavioral context: the exact return structure (campos: data, siglaComissao, count, reunioes with nested fields) and the scope (date-based with optional committee filter). This goes beyond annotations and helps the agent understand what to expect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact paragraph that front-loads the core purpose and parameters, then lists the return format, and finally gives sibling guidance. Every sentence adds new value; there is no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has only two optional parameters, a provided output schema, and rich annotations, the description covers all necessary context: what the tool does, how to use it (defaults, filters), what it returns, and how it relates to similar tools. No gaps remain for the agent to infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already describes each parameter. However, the description adds meaning: it notes the default value for 'data' (padrão: hoje) and that 'siglaComissao' is optional. This extra context, especially the default, helps the agent know it can be omitted for today's agenda.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it obtains the agenda of all committee meetings on a date, with an optional committee filter. It lists the return fields and distinguishes itself from siblings (senado_reunioes_comissao and senado_reuniao_comissao), leaving no ambiguity about its function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly mentions the default date (today) and the optional filter. It provides clear guidance on when to use alternative tools: 'Para o histórico de uma única comissão por período use senado_reunioes_comissao; para detalhes de uma reunião use senado_reuniao_comissao com o codigo'. This covers both when to use this tool and when not to.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is clear. The description adds value by detailing the return structure (data, escopo, count, sessoes) and session fields (codigo, data, hora, tipo, situacao, pauta), which goes beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one dense paragraph that front-loads the purpose, then returns structure, then usage, then related tools. Every sentence earns its place with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 3 parameters, no required fields, and an output schema, the description fully explains the return structure, parameter behavior, and related tools. It is complete for effective use without needing additional context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, providing baseline of 3. The description adds meaning by explaining the escopo enum values (dia, mes, cn), default for data (today), and that dataFim is only for escopo=cn. This contextualizes the schema beyond its minimal descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool obtains the agenda of plenary sessions for Senate or National Congress, with specific fields returned. It distinguishes itself from siblings like senado_encontro_plenario and senado_resultado_plenario by mentioning when to use those instead.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells when to use this tool versus alternatives (e.g., 'Para o resultado já apreciado use senado_resultado_plenario; detalhes de uma sessão via senado_encontro_plenario'). Also explains parameter defaults and scope behavior ('Use escopo dia/mes/cn; sem data assume hoje').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (readOnlyHint, etc.), the description discloses the return structure, ordering, filters behavior (partial search without accents), and defaults/limits. It also explains that only authors with processes in tramitação are included. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise: three sentences that front-load the purpose and ordering, then detail return structure and parameters. No extraneous information, every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool that lists authors with filters and ordering, the description covers all necessary aspects: what it returns, filtering, ordering, limit constraints, and cross-reference to other tools. It is complete given the presence of an output schema (implied by the described return structure).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (each parameter documented), but the description adds value by explaining that 'nome' is a partial search without accents, 'uf' is a 2-letter code, and 'limite' has a default of 50 and max 1000. This goes beyond the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists parliamentary authors of pending processes, ordered by production (most matters first). It distinguishes itself from siblings like senado_listar_senadores (which lists all senators) by specifying it only includes authors with active processes and providing a specific ordering.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides usage guidance by stating the output 'codigo' can be used in 'senado_obter_senador' or 'senado_search_processos'. It does not explicitly mention when not to use it but the context is clear. A more explicit differentiation from senado_listar_senadores would improve it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds behavioral context: returns structure { count, normas } with specific fields, and that it returns error if no parameters. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise with 4 sentences, each adding value: main function, output, constraint, and links to related tools. No fluff, but could be slightly more streamlined.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists, the description covers the return structure, required parameters, and related tools. It does not mention pagination or sorting, but for a query tool this is acceptable. Completeness is good.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with each parameter having a description. The description repeats the parameter names and adds the constraint that at least one is required, but does not add deeper semantic meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches for federal legal norms by tipo, numero, ano, or data. It specifies the resource (normas jurídicas) and distinguishes from siblings by mentioning use of codigo for senado_obter_legislacao and valid types in senado_tabelas_referencia.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly requires at least one parameter, else returns error. It provides context on when to use this tool vs. related tools, but does not explicitly state when not to use it. The reference to sibling tools for detail and reference adds guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses read-only, idempotent, non-destructive behavior consistent with annotations. Adds details on return structure, pagination (default 100, max 500, truncation warning), default ordering, and the need for at least one criterion.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single well-structured paragraph that front-loads core purpose, then provides examples, return format, sibling link, and limit details. Every sentence adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (11 optional parameters, output schema, many siblings), the description covers all necessary aspects: usage, parameter guidance, return structure, pagination, and cross-reference to sibling tool. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds meaningful context beyond schema: explains when to use each parameter (e.g., for recent matters), notes default order, and provides usage patterns that integrate multiple parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Describes exactly what the tool does: search legislative matters by type, number, year, keywords, author, date range, or status, requiring at least one criterion. Clearly differentiates from sibling senado_obter_materia by specifying when to use each.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use examples like 'matérias recentes sobre X' with suggested parameters, and when-not-to-use by stating not to call details just to list results. Clearly directs to sibling for detailed lookup.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses behavioral details beyond annotations: aggregated vs detail mode, ordering, truncation with warning, and partial search filters. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise yet comprehensive. Front-loaded with purpose, then detailed return structure, filtering options, and a practical hint. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Fully covers the tool's complexity: all 8 parameters, return formats, filtering, truncation, and cross-reference to another tool. No gaps given the existing schema and annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds meaning beyond the schema: explains default mode, limits, return shapes for different modes, and that filters support partial search. Schema coverage is 100% but description still enriches understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns CEAPS expenses for senators in a given year. It specifies the return structure and differentiates from other senado tools by focusing on parliamentary expense data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance on when to use this tool, including hints to obtain codSenador via senado_listar_senadores and mentions the default aggregation mode.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds behavioral details: it explains the return format, limits (default 100, max 500), and error conditions for invalid type-section combinations. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized, with each sentence serving a purpose. It is well-structured: purpose first, then parameter details, return format, usage note, and error condition. No redundant or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (multiple parameters, type-section combinations, pagination via limite, output schema), the description covers all essential aspects: it explains the purpose, parameter meanings, return structure, limits, prerequisites, and error handling. The output schema exists but the description provides enough context on the return fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds meaning beyond the schema by explaining the semantics of each parameter: id is from lists, tipo enumerations with descriptions, secao with restrictions (aditivos only for contratos, acionamentos only for atas), and limite with default and max. This significantly aids understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool details a specific section of a contracting. It uses specific verbs and resource names, and distinguishes itself from sibling tools by noting that the id should be obtained from 'senado_contratos' or 'senado_contratacoes_lista'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use the tool (to get details of a contracting section) and prerequisites (obtain id from list tools). It does not explicitly state when not to use, but the context is sufficient. No explicit alternatives are given, but the prerequisite hints at the workflow.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already confirm readOnly, idempotent, not destructive. Description adds details: filter applied via Worker, return structure differences between tipos, limit truncation with aviso, and empty list behavior. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with purpose, then details. No extraneous information. Efficient and clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all key aspects: types, filtering, limit, empty lists, return structure, and cross-reference to sibling tool. Output schema exists but description still explains shape differences, making it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with good parameter descriptions. Description adds extra context: filter applied to all fields via Worker, default limit, and truncated results. This enhances understanding beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it lists three types of contract records (atas de registro de preço, notas de empenho, menores aprendizes) from Senado, with optional text filter. It distinguishes from sibling senado_contratacao_detalhe, which is for deeper detail.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use (listing records) and when not to (for deepening a specific record, use senado_contratacao_detalhe). Also mentions behavior for empty lists, providing clear usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds value by specifying the limit behavior (default 50, max 500, truncation with `aviso`) and the structure of returned items (id, numero, objeto, empresa, etc.). No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: three sentences cover purpose, return structure, and usage guidance. No filler. Front-loaded with the most important information. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, filters, return structure (top-level and item fields), limit behavior, and how to use the result for further detail. Output schema exists, so full return value documentation is not required. The description is complete for a search tool of this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds context by listing the filterable fields and noting that filters are applied upstream. It also explains the `limite` parameter with default and max. This provides additional meaning beyond the individual parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states 'Busca contratos administrativos do Senado por fornecedor, CNPJ, ano, número, objeto ou mão de obra', clearly identifying the tool's verb (search) and resource (administrative contracts). It distinguishes from sibling tools by directing the user to use the returned `id` with `senado_contratacao_detalhe` for more details.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance on when to use the tool (to search contracts with various filters) and when to use alternative (for detailed contract info, use `senado_contratacao_detalhe`). Also explains the limit parameter behavior with default and maximum, and the truncation warning via `aviso`.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, open-world, idempotent, and non-destructive hints. The description adds value by specifying the exact return structure with field names.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no extraneous content. The purpose is front-loaded, and the structure is clear and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity, the description covers all necessary aspects: input parameters, output structure, and sibling references. Output schema exists, so description complements it well.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions and patterns. The description reinforces that both parameters are mandatory and provides the date format YYYYMMDD, but does not add substantial new meaning beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Lista todos os discursos realizados em plenário num período de datas' with specific verb, resource, and scope. It also distinguishes from sibling tools by explicitly naming alternatives for filtering by senator or getting full text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use (listing all speeches in date range) and when-not-to-use (for specific parliamentarian use `senado_discursos_senador`). Naming alternatives gives clear guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint false. The description adds value by explaining the return structure (codigoSenador, tipo, count, discursos with fields), stating that no full text is provided, and clarifying behavior for different tipo values (discursos vs apartes). This goes beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is a single coherent paragraph, front-loaded with purpose. Every sentence adds value: purpose, parameter explanation, output format, cross-tool references. Not overly long, but packed with information. Could be slightly more structured, but very efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (5 params, output schema described), the description is largely complete. It covers purpose, parameters, output, and cross-tool usage. Does not mention error handling or pagination, but for a list tool with annotations, it is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, baseline 3. Description adds meaning by explaining the tipo parameter choices and default, and clarifying that dataInicio/dataFim are for period filtering. It also mentions casa filter in the purpose sentence. Adds value beyond schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists pronouncements of a senator, with filters. It distinguishes from siblings by referencing senado_listar_senadores for codigoSenador and senado_discurso_texto for full text, implying this tool is for listing per-senator speeches.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context: use when you need pronouncements of a specific senator, filterable by period and house. Mentions alternative for full text (senado_discurso_texto) and prerequisite (senado_listar_senadores). Does not explicitly state when not to use, but the context is strong.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint as false. Description adds that it returns text, but does not elaborate on other behavioral aspects (e.g., rate limits). With annotations covering safety, a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core purpose and return type, followed by prerequisite guidance. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite tool simplicity, the description covers purpose, prerequisite steps, return format, and parameter source. Annotations and output schema cover the rest. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the parameter description ('Código do pronunciamento') is clear. The description adds context on where to get the parameter value, but does not add semantic detail beyond the schema. Baseline 3 is correct.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it retrieves the full text of a specific speech, explicitly distinguishes from sibling tools that list speeches, and specifies the return structure.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to obtain the codigoPronunciamento first via sibling tools (senado_discursos_senador or senado_discursos_plenario). While it doesn't state when not to use, the guidance is clear and sufficient for this retrieval tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, openWorld, idempotent, non-destructive. Description adds return structure, ordering, and constraints (codigoParlamentar only works with autoria). No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is front-loaded with purpose and return shape, medium length, no redundant phrasing. Could be slightly more concise but overall well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool is simple retrieval with clear parameters and output schema. Description covers all necessary behavioral aspects, return format, and usage context. Fully complete for an info tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%; description adds context (e.g., codigoParlamentar only for autoria) but does not significantly extend schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it provides statistics on distribution of matters by committee, with type and optional filter. It distinguishes from sibling tools by mentioning the prerequisite tool senado_listar_comissoes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states usefulness for measuring legislative workload and that committee sigla should be obtained via senado_listar_comissoes. Lacks explicit when-not-to-use, but context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=true, openWorldHint=true, idempotentHint=true. The description adds significant behavioral context: explains modes, status behavior (including the limitation on encerrada), ordering criteria, default values, and return format. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sentences and front-loaded purpose. It is slightly verbose but each sentence adds value. Could be slightly more concise without losing clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (6 parameters, modes, status nuances, defaults, limitations) and presence of output schema, the description covers all necessary aspects: modes, ordering, status, defaults, limitation, return format, and sibling tool reference. Complete for an analysis tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds semantic detail beyond schema, e.g., explaining how percentualMinimo and margemPolarizacao work in each mode, and the meaning of the return object.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool analyzes public consultations by agreement degree (consenso or polarizada), differentiating from sibling tools like senado_ecidadania_obter_consulta. It specifies the verb 'analisa' and the resource 'consultas públicas abertas (matérias em tramitação)'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use each mode, the meaning of status options (aberta, encerrada, todas), and mentions the sibling tool for detail. It provides defaults and limitations (e.g., closed consultations before first load not captured), but lacks explicit when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, etc. The description adds that data is updated weekly, treats status as historical, and returns specific structure (count, referencePeriod, consultas). No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is well-structured with bold keywords, uses bullet-like paragraphs, and is concise given the complexity. Could be slightly shorter but still efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (5 params, output schema present), the description fully covers purpose, usage, parameters, return structure, and behavioral traits. Output schema exists, so return value details are not needed in description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 5 parameters have descriptions in the input schema (100% coverage). The description adds explanatory context about 'ranquear por aquele estado' for 'uf', 'ranking' for 'ordenarPor'/'ordem', and clarifies 'materia' filter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly defines the tool as an archive of historical votes with breakdown by UF, and explicitly distinguishes it from the sibling 'senado_ecidadania_listar_consultas' which deals with current consultations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance on when to use this tool (historical archive) vs. the sibling, explains the meaning of the 'status' field, and elaborates on parameter usage like 'uf' for filtering and ranking.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds behavioral context: return format, status transitions, limitation that encerradas before first ingestion are not captured. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single paragraph packed with information, every sentence adds value. Could be slightly more structured but still appropriately sized and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (3 parameters, output schema present, many sibling tools), the description is complete. It explains return format, parameter meanings, limitations, and links to other tools. Output schema covers return fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so baseline 3. Description adds meaning beyond schema: explains default status 'aberta', describes encerrada/todas, and notes the limitation about encerradas before first ingestion. Adds context about status lifecycle.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource ('consultas públicas do e-Cidadania') and action ('Lista'), and distinguishes from sibling tools by mentioning alternatives for detail (obter_consulta) and analysis (consultas_analise).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use this tool vs alternatives: for a list of consultations, for detail call senado_ecidadania_obter_consulta, for analysis call senado_ecidadania_consultas_analise. Also explains default status and filtering options.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds behavioral context beyond annotations: data persistence (corpus in D1), weekly updates, scale (thousands), inclusion of closed events, and return structure. No contradictions with readOnlyHint or idempotentHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single paragraph, front-loaded with core purpose, followed by return format, filters, and usage scenarios. Every sentence adds value; no superfluous content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all essential aspects: what is returned (count and eventos with fields), available filters (status, comissao, limite), ordering options (data, comentarios), update frequency, and hints for related actions (get event detail). Output schema exists but description still provides sufficient detail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, the description still adds value: default limit of 20, 'comissao' as abbreviation, default order for 'ordem', and concrete examples for ordering by comments via 'ordenarPor' and 'ordem'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it lists interactive events from e-Cidadania (audiências, sabatinas, lives) and distinguishes from sibling 'senado_ecidadania_obter_evento' for detailed retrieval. Provides context about the complete corpus and update frequency.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly describes when to use this tool (listing events) and directs to a specific sibling tool for detailed event info. Also explains how to use filtering and ordering, including a ranking use case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds behavioral context beyond annotations: describes the corpus size (~150k ideas), update frequency (weekly), inclusion of closed/converted ideas, and field restrictions (null for author/date in list). All consistent with readOnlyHint=true.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured: front-loaded purpose, then output details, filtering, ordering, and sibling reference. Each sentence provides essential information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists, the description covers return format (count, ideias with fields), corpus scope, update cadence, and limitations. No missing critical information for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 5 parameters have descriptions in schema (100% coverage). Description adds extra meaning by clarifying default limit (20), recommending ordering by 'apoios' for ranking, and noting which ordering fields are available in the list vs. detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists legislative ideas from e-Cidadania, specifying the complete corpus and distinguishing itself from the detail tool (senado_ecidadania_obter_ideia) and other list tools like senado_ecidadania_listar_consultas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly mentions when to use this tool (for listing), provides filtering and ordering guidance, and directs users to the sibling tool for full details. It also explains limitations (author and date are null in list).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds value by specifying the exact return fields and noting that some fields may be null. It does not discuss rate limits or authentication, but annotations cover the safety profile adequately.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single paragraph that efficiently conveys purpose, parameters, and return format. It is front-loaded with the main action but could be broken into multiple sentences for improved readability. However, there is no superfluous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description explains the tool's return object fields, parameter source, and notes about nullable fields. For a simple retrieval tool, this covers all necessary context for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a single required parameter 'id' described as 'ID da consulta pública'. The description adds context by explaining that the id comes from specific sibling tools, and also mentions the return structure, which helps infer the parameter's purpose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves details of a specific public consultation from e-Cidadania, with a specific verb ('Obtém') and resource. It lists the return fields, distinguishing it from sibling tools like senado_ecidadania_listar_consultas and senado_ecidadania_consultas_analise.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly instructs to obtain the 'id' parameter via senado_ecidadania_listar_consultas or senado_ecidadania_consultas_analise, providing clear prerequisite guidance on when to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint as true and destructiveHint as false. The description adds value by detailing the returned fields, including conditional fields like videoUrl ('quando houver'), and the maximum number of pauta items. This goes beyond the annotations and helps the agent understand what to expect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description consists of two concise sentences. The first sentence states the purpose and lists returns, the second provides a prerequisite. No unnecessary words, and the structure is front-loaded with the key action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the low complexity (single parameter, no enums), combined with rich annotations and an output schema, the description is complete enough. It covers the return fields and the prerequisite. Minor gaps like explaining status values are not critical for this simple retrieval tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with the parameter 'id' having a description 'ID do evento'. The description reinforces that the ID must be obtained first, but adds no new semantic meaning beyond the schema. Baseline score of 3 is appropriate since the schema already documents the parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Obtém o detalhe de um evento interativo do e-Cidadania', which is a specific verb+resource. It distinguishes from the sibling tool 'senado_ecidadania_listar_eventos' by mentioning that the ID should be obtained from that tool. The return fields are listed, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells the agent to obtain the ID via 'senado_ecidadania_listar_eventos' before using this tool, which is direct usage guidance. It does not mention when not to use it or provide alternatives, but the context is clear enough for appropriate selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds valuable behavioral context beyond annotations, notably that the 'descricao' field is truncated to ~2000 characters and lists the returned fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no waste. The purpose and key usage instruction are front-loaded, making it easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, clear annotations, and an output schema), the description is complete: it explains the return fields, a behavioral nuance (truncation), and the prerequisite step. No gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a single parameter 'id' described as 'ID da ideia legislativa'. The description does not add significant extra meaning beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Obtém o detalhe de uma ideia legislativa do e-Cidadania' with a specific verb and resource. It distinguishes itself from the sibling tool 'senado_ecidadania_listar_ideias' by noting the prerequisite to obtain the ID first.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to obtain the ID via 'senado_ecidadania_listar_ideias' before using this tool, providing clear context on when to use this tool versus its sibling.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate a read-only, idempotent, non-destructive operation. The description adds behavioral context by explaining internal filtering logic and output structure, enhancing transparency beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (5-6 sentences), well-structured with purpose first, then output format, then parameter details. Every sentence adds useful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's purpose, input parameters with defaults, return structure, and next steps. With an output schema available, it is fully complete for an AI agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 100% schema coverage, the description adds value by summarizing criteria, explaining defaults, and clarifying how parameters affect behavior (e.g., 'apenasEmTramitacao padrão true → considera só consultas abertas').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool suggests topics for a monthly public poll, analyzing consultations and ideas, and filtering by engagement criteria. It distinguishes itself from sibling tools like senado_ecidadania_listar_consultas by focusing on selecting top suggestions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use the tool (to get suggestions) and what to do next (use senado_ecidadania_obter_consulta or senado_ecidadania_obter_ideia). It does not mention exclusions or when not to use it, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and destructiveHint, so description adds value by detailing return structure (count, total, empresas with specific fields and max 30 contracts). No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two efficient sentences with all relevant information, front-loaded with action, no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given complexity, annotations, and output schema, the description covers search behavior, required parameters, return format, limit, and cross-references to other tools. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, description adds context: min 3 chars for nome, partial search for cnpj, default and max for limite, and clarifies that one of nome/cnpj is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches for companies contracting with the Senate by name or CNPJ/CPF, distinguishes from siblings by referencing detailed tools for further information.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states that either nome or cnpj is required to avoid querying the full database, and suggests using the returned id with other tools for details. Provides clear when-to-use and when-to-use-alternatives guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. Description adds behavioral traits: encontro may be empty, error on nonexistent codigo, fields vary by secao. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is detailed but front-loaded with purpose. Each sentence adds value. Slightly verbose but not excessively so.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists and context signals, description covers return structure, variations, error cases, and input source. Fully adequate for complex tool with many siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%. Description adds meaning beyond schema by explaining how secao values affect output and how codigo is obtained from sibling tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description specifies verb 'retorna' and resource 'encontro legislativo (sessão de plenário)'. It distinguishes from siblings by mentioning how to obtain codigo and listing secao options.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states that codigo should be obtained from senado_agenda_plenario or senado_resultado_plenario, providing clear context. Lacks explicit when-not-to-use, but gives sufficient guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes return structure (tipo, modo, ano, totalLinhas, agregado[] or despesas[]/receitas[]), truncation with aviso, and ordering. Annotations confirm read-only, safe behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single dense paragraph with clear flow: purpose, return format, usage, differentiation. Efficient but could be more structured with bullets for readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all key aspects: data scope, parameter interplay, result format, filtering advice, and sibling differentiation. Output schema likely fills remaining gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters, but description adds context: links modo to tipo, explains ano for volume reduction, and notes default limite.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it covers Senate budget execution (expenses and revenues), lists year ranges, and distinguishes from sibling tool senado_orcamento_parlamentar.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs when to use each tipo with corresponding modos, recommends filtering by ano before detalhe, and warns against confusion with another tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and destructiveHint false. Description adds that data is from 2013 onward and details the return structure, but does not contradict annotations. It provides useful context without overstating effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences that front-load the purpose and gradually add details. Every sentence is informative with no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description fully explains the return structure (fields and meaning) and optional filters. It also mentions the starting year and relation to sibling tool, making it complete for an agent to understand the tool's behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions for all 4 parameters. Description repeats the schema info (partial search for nome, default/max for limite) but adds no new meaning beyond a concise summary. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool returns overtime payments for Senate employees by year/month, with specific verb 'retorna' and resource 'horas extras pagas'. It distinguishes from sibling tool 'senado_remuneracoes_servidores' by explicitly directing users there for full compensation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use (list overtime for a given month/year) and when-not-to-use (for full compensation, use sibling). Also mentions optional filters and defaults.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, etc. The description adds behavioral details: returns raw records, default/max limit, and authentication implications (none mentioned, but no contradiction).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: two sentences front-load purpose, include usage example, limit info, and sibling reference—no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists, the description fully covers behavior: return format, error condition, limit details, and relationship to sibling tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage, and description adds value with format examples (e.g., '19/2018') and clarifies that at least one filter is required but both are optional.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches for Senate bidding processes by exact number or object text, explicitly differentiating from the sibling tool 'senado_contratos'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use (by number or object text) and when-not (no filter returns error), plus an alternative for the resulting contract: use senado_contratos.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds behavioral context by detailing the return structure ({count, liderancas}) and the fields within each item, which is beyond the annotations. There is no contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured: two sentences, the first stating purpose and return format, the second giving filtering and alternative. It is front-loaded with the most important information and contains no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (4 parameters, optional filters) and the presence of annotations and output schema (implied by the return structure described), the description covers the essential aspects: purpose, filters, default behavior, return format, and alternative tool. It is complete for the agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with each parameter having a basic description. The description adds value by consolidating the filtering options and stating the default behavior (returns all without filters), which provides additional context beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: listing leadership roles in the Senate and National Congress. It specifies the verb 'list' and the resource 'lideranças', and distinguishes from the sibling tool 'senado_listar_blocos' by mentioning it is for blocos composition.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit filtering options (casa, codigoParlamentar, vigente, siglaTipoLideranca) and states that without filters it returns all. It also explicitly names an alternative tool ('senado_listar_blocos') for blocos composition, giving clear when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description adds the return format and structure (count, blocos, each with nested partidos). This provides context beyond annotations, but no behavioral surprises.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first states purpose and return structure, second gives usage guidance and links to sibling tools. No waste, front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and existing output schema, the description fully covers what the tool does and how to use it. It also references related tools for next steps, making it contextually complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so the description cannot add meaning to them. With zero parameters and 100% schema coverage, the baseline is 4. The description correctly states there are no inputs, so no further elaboration needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool lists all parliamentary blocs and their member parties. Explicitly mentions the return structure with fields like count, blocos, codigo, nome, etc. Differentiates from sibling tools by referencing senado_obter_bloco for detail and senado_liderancas for leadership.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance: use this tool to discover a bloc's codigo, then use senado_obter_bloco for details; for leadership, use senado_liderancas. This helps the agent decide when to call this tool versus alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only and non-destructive behavior. The description adds that the endpoint only brings active commissions, regardless of the filter, and explains the return shape. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loaded with purpose and filters, then details return format and usage guidance. Every sentence is informative and concise, with no extraneous text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (two optional parameters, output schema exists, annotations cover safety), the description fully covers purpose, usage, and return structure. It also links to sibling tools, making it complete for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both parameters. The description adds context by stating that the endpoint only returns active commissions, implying that the ativa filter is redundant if set to true, and that false yields empty. This adds practical meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists active commissions with filters for tipo and ativa, and specifies the return structure with fields like codigo, sigla, nome, tipo, casa, and ativa. It distinguishes itself from siblings by noting it is used to discover the sigla required by senado_obter_comissao and senado_reunioes_comissao.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says to use this tool to discover the sigla needed by senado_obter_comissao and senado_reunioes_comissao, providing clear contextual guidance. It also warns that the endpoint only returns active commissions, so setting ativa=false results in an empty list, which helps correct usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.