Painel Sintético Concorde

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

With no annotations provided, the description carries full burden. It explains the tool is a deterministic heuristic screening and mentions the classification output, but it does not disclose any potential side effects, required permissions, or error handling. It is adequate but lacks depth.

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 with three sentences, front-loading the key classification categories and usage context. Every sentence adds value 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?

The tool has simple inputs and no output schema, but the description does not specify the output format or any return values. It covers purpose and usage well but could be more complete by describing the likely output structure or required access rights.

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 no additional meaning beyond what the schema already provides for the single parameter 'pergunta', other than giving an example that is already in the schema description.

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 verb 'classifica' and the resource 'pergunta de pesquisa', and specifies three distinct output categories ('inferivel', 'arriscado', 'humano'), making the tool's purpose very clear. It distinguishes itself from sibling tools that deal with facts, personas, distributions, etc.

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 when to use the tool ('Use antes de rodar um focus group') and provides guidance for edge cases ('casos de borda devem ir para validação humana'). However, it does not explicitly state when not to use it or compare directly to siblings.

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?

No annotations are provided, so the description must disclose behavioral traits. It describes the search modes but does not mention read-only nature, rate limits, authentication, or side effects. Acceptable but not thorough.

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 short sentence with a list of modes, front-loading the main action. It is concise but could be better structured with clear separation of modes.

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?

There is no output schema, so the description should explain return values. It does not describe the result format or pagination. Also, it does not differentiate from siblings like 'filtrar_personas'. Incomplete for a search 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%, so baseline is 3. The description adds value by defining what each search mode does (e.g., 'busca em métrica/fonte/corpo' for texto), enhancing the schema's property 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 searches in 105 fatos estatísticos and lists the three modes (text, axis, persona_id). It distinguishes from siblings like 'get_personas' by focusing on facts, but could be more explicit about the resource type.

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 parameter (texto livre, eixo, persona_id), but does not provide guidance on when not to use this tool or alternatives among the sibling tools. Lacks exclusions or context for 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?

With no annotations provided, the description carries the full burden. It discloses that the tool returns count and mini-profiles, is deterministic, and that empty filter returns all. No behavioral side effects are mentioned, but the read-only nature is implied.

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 the purpose, and every word adds value. No fluff.

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 of a DSL filter and no output schema, the description adequately explains input format and return type. It mentions the sibling context implicitly, but could be more explicit about how it differs from get_personas and sortear_amostra.

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%, and the description adds value beyond the schema: it provides an example for filtro, explains the DSL syntax, and clarifies that limite controls the maximum mini-profiles returned.

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 filters personas using a deterministic DSL, provides a concrete example, and distinguishes from sibling tools like get_personas (which likely returns all) and sortear_amostra (random sampling).

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 gives an example usage, explains that empty filter returns all, and mentions the return type. It implicitly tells when to use (filtering) but lacks explicit comparisons to siblings or when-not-to-use scenarios.

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?

No annotations are provided, so the description carries the full burden. It mentions listing files (implying read-only), but does not disclose any side effects, required permissions, or other behavioral traits. The description is minimal and does not fully inform the agent about what happens when calling the tool.

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 very short (one sentence) and avoids redundancy. It packs the key purpose and a behavioral note into a concise format. However, it could be slightly clearer with separate sentences for listing vs retrieving a specific file.

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 simple tool with one optional parameter and no output schema, the description covers the main action and parameter behavior. However, it lacks details about the return format (e.g., file list, CSV contents) and does not explain what 'manifest.md' or 'taxas' are. The overall context is sufficient but not 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 a description for 'arquivo'. The description adds behavioral context: 'Sem nome, lista os arquivos' clarifies that omitting the parameter lists all files. This goes beyond the schema which only states the parameter values. The description is helpful for understanding parameter behavior.

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 states the tool retrieves calibration tables (distribution CSVs and fee register) and lists files. The verb 'lista' makes the action clear. However, it could be more specific about what is returned when a name is provided vs not. It distinguishes from siblings (get_personas, etc.) by focusing on calibration 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?

The description offers no guidance on when to use this tool versus siblings. It does not provide context about prerequisites or alternatives. The usage is implied (listing calibration files), but without explicit direction, agents may misuse 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?

The description discloses that the tool can return a single profile or a list of available banks, but without annotations, it omits details on authentication, rate limits, or any potential side 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?

The description is a single sentence with parenthetical details, front-loading the main purpose and efficiently conveying both the data included and the parameter-dependent behavior.

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 simple tool with one optional parameter and no output schema, the description adequately explains the scope (12 banks) and the data fields (cadastro, volumetria, reputação, reviews), though it could elaborate on the output 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?

The schema covers the parameter 'nome' with examples; the description adds crucial context that omitting the parameter triggers a list of available institutions, enhancing semantic understanding 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 retrieves a financial institution profile (ficha) including registration, volumetrics, reputation, and reviews. It specifies 12 banks and distinguishes behavior when no name is provided (lists available), setting it apart from siblings like visao_geral.

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 implies usage for querying 12 specific banks and suggests listing when no name is given, but it does not provide explicit when-to-use or when-not-to-use guidance, nor alternatives among siblings.

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?

No annotations provided, so description carries full burden. Discloses return components, capacity limit of 10 IDs, and important caveats about fact interpretation. Does not cover authentication, idempotency, or rate limits, but these are not critical for a read-only data retrieval tool.

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, no wasted words. Front-loaded with main purpose and result components. Important caveat is clearly flagged with 'IMPORTANTE'. Structure is efficient and 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 no output schema, description adequately explains return structure by listing key components (attributos, Grounding, História). Includes critical interpretation guidance. Could be more detailed on return format, but sufficient for a simple list 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 a clear example for the single parameter 'ids'. Description adds value by summarizing what the output contains (attributes, grounding, history) and the important interpretation note, which goes beyond the schema's parameter description.

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 returns complete profiles of up to 10 personas by ID, listing components (attributes, grounding with facts/sources, history). Distinguished from siblings like filtrar_personas (filtering) and buscar_fatos (facts only) through specific resource and action.

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 'Use para dar voz às personas com ancoragem nos dados' (use to give voice to personas anchored in data). Provides critical interpretation guidance about _composicao_ and _referencia_ facts. Does not explicitly state when not to use or name alternatives, but siblings are listed in 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?

No annotations are provided, so the description carries the full burden. It discloses the non-populational nature and intended use as illustration, which is good. However, it does not explicitly state whether the tool is read-only or if it has any side effects, leaving some ambiguity.

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, with two sentences that front-load the key information. Every sentence has a clear purpose: listing themes and providing usage caveat. No redundant or unnecessary 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 parameters, no output schema), the description covers the main aspects: what the tool does, available filters, and a caveat about representativeness. It does not explicitly state the return format, but the nature of 'vozes' implies a list of text excerpts, which is acceptable.

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 descriptions are brief. The description adds value by enumerating the possible theme values, explaining default behavior when tema is omitted, and confirming that completo includes full text. This goes beyond the schema's basic 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 real verbatim voices (reviews, reports) filtered by specific themes, with an explicit list of themes. It distinguishes from sibling tools by focusing on qualitative language data rather than facts or distributions.

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: use this tool to get illustrative language excerpts by theme. It warns against using it for statistics, which is helpful. However, it does not explicitly contrast with sibling tools or state when not to use 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?

No annotations provided, so description must disclose behavior. It mentions randomness and representativeness but does not explicitly state the operation is read-only, if state is modified, or any prerequisites. This is acceptable but could be clearer.

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 front-loaded action. No redundant words. Every element 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?

Without an output schema, the description should state what the tool returns (e.g., list of personas). It also does not clarify the difference from sibling 'filtrar_personas', which may return all matching personas rather than a random sample.

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 no additional parameter explanation beyond what the schema already provides (e.g., 'n' as sample size, 'seed' for reproducibility, 'filtro' for DSL filter).

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 action 'sorteia uma amostra aleatória de personas' and mentions optional filtering via DSL, distinguishing it from sibling tools like 'filtrar_personas'. However, it does not specify the output format (e.g., list of IDs or objects).

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 phrase 'o painel já reflete as distribuições reais, então a amostra uniforme é representativa do recorte' provides implicit guidance that this tool is appropriate for obtaining representative random samples. It lacks explicit when-not-to-use or alternative tool references.

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?

No annotations exist, and the description only says it gives an overview. It does not disclose behavior beyond that, such as response format, side effects, or authorization needs. For a tool with no destructive actions, this is adequate but minimal.

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 extremely concise—a single sentence that conveys purpose and usage instruction. Every word contributes to clarity, 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 zero parameters and no output schema, the description fully informs about the tool's role as an overview provider, including what it covers (counts, fields, usage). It is complete for its simplicity.

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?

There are no parameters. Baseline score of 4 is appropriate as the description does not need to add parameter-level details.

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 that the tool provides an overview of the dashboard including counts, available fields, and how to use other tools. This distinguishes it from sibling tools which are specific actions like filtering or searching.

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 'Chame primeiro' (Call first), indicating the tool should be invoked before others. While it doesn't explicitly state when not to use it, the context is clear and sufficient.

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