NEXO CAUSAL: perícia e ciência forense

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

The annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety needs no restating. Beyond that the description adds nothing behavioral: no mention of ordering guarantee, how many items come back by default, or pagination. With a maximum of 30 in the schema going unaddressed, the behavioral picture stays thin.

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?

A single short sentence with the resource front-loaded and the optional filter scope appended. No filler, no restatement of the title beyond what is necessary to convey 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?

This is a simple two-parameter read tool with annotations and no output schema, so expectations are modest. However, with no output schema the description should say what a returned article entry looks like or at least confirm ordering by recency, and it does neither. It is adequate to call the tool but leaves the response shape entirely unknown.

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 only 50%: 'assunto' is documented in the schema, while 'limite' has constraints (1-30, default 10) but no prose. The description's phrase 'de todos os assuntos ou de um só' does convey that the subject filter is optional and that omitting it widens the result to everything, which is real added meaning. It says nothing about the limit parameter's effect on result size, leaving half the surface to the schema's numeric constraints.

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 names a specific verb and resource ('Lista os artigos mais recentes') and states the scope: all subjects or a single one. An agent can tell this is a recency-ordered listing rather than a text search or a single-article read. It stops short of naming the sibling 'buscar_artigos' to sharpen the contrast, so it is clear but not fully differentiated.

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 describes only what the tool returns, not when to choose it over 'buscar_artigos', 'ler_artigo' or 'listar_assuntos'. There is no stated precondition, exclusion, or alternative. The word 'recentes' hints at browsing-latest usage, but that is inference rather than 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 the read-only, idempotent, closed-world safety profile, so the bar is lower. The description adds real value beyond them by disclosing which fields are matched and exactly what the response contains (título, data, assunto, resumo, fonte, endereços de página e Markdown), which matters since there is no output schema.

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, zero filler, front-loaded with the search capability and followed by the return payload. Every clause 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?

With no output schema, the description adequately covers return values, and it scopes the searchable fields. Gaps remain around result ordering, the meaning of limite, and behavior on zero results, but nothing blocks a correct call.

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 67%; consulta and assunto are already described in the schema (assunto even points to listar_assuntos), and the description adds little beyond them. The undocumented parameter, limite, is never mentioned in the description either, so the description does not compensate for the coverage gap.

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?

States a specific verb (busca) and resource (artigos do NEXO CAUSAL) plus the fields searched (título, resumo, marcadores) and accepted languages, so the agent knows exactly what the tool retrieves. It does not explicitly distinguish itself from siblings like artigos_recentes or ler_artigo, which keeps it from a 5.

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?

Usage is implied: keyword search is the clear entry point versus browsing recent articles or reading a single article. It references listar_assuntos indirectly through the assunto parameter, but never states when to prefer artigos_recentes or ler_artigo, nor any exclusions.

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 cover safety (readOnly, idempotent, closed-world, non-destructive), so the bar is low. The description still adds value by disclosing what each result contains (definition, English equivalent, citing articles), which matters because there is no output schema. It does not describe ordering of results or how the limit interacts with matching.

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?

A single well-formed sentence with the purpose front-loaded and the return contents neatly bracketed. No filler or repetition, though the brevity leaves no room for the missing usage guidance.

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 two-parameter lookup with no output schema, the description covers purpose and return shape reasonably well. However, the undocumented 'limite' parameter and the absence of any guidance on matching behavior (partial term, Portuguese vs English) leave gaps an agent must guess at.

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 only 50%: 'termo' is documented in the schema, but 'limite' (1-20, default 5) has no description anywhere. The tool description says nothing about either parameter, so it fails to compensate for the coverage gap.

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?

States a specific verb ('Procura') plus resource ('termos de perícia no glossário do NEXO CAUSAL'), and even enumerates what each entry contains (definição, equivalente em inglês, artigos). The glossary resource is distinct enough from siblings like buscar_artigos and ler_artigo that an agent can route correctly, though no sibling is named explicitly.

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?

Usage is only implied: the agent must infer that this is for term/definition lookup rather than article retrieval. There is no explicit when-to-use statement, no mention of quando preferir buscar_artigos ou ler_artigo, and no prerequisites given.

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, non-destructive and closed-world behavior, so the safety profile is covered. The description adds value beyond that by disclosing what the response contains (full text in Markdown plus date, subject, original source and citation form), which is meaningful since no output schema exists. It stops short of describing failure or not-found 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?

A single well-formed sentence with no filler, and the core action (returns the full text in Markdown) is front-loaded ahead of the metadata details. It could be tightened slightly by naming the sibling search tool, but nothing is wasted.

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 one-parameter, read-only fetch tool with full schema coverage and rich annotations, the description supplies everything an agent needs: what is returned, in what format, and what accompanying metadata comes with it. No output schema is required because the return content is described in prose.

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 is documented with both an example slug and the alternative page-address form, so the schema carries the burden. The description adds nothing further about the identifier format, so baseline 3 applies.

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 a specific verb and resource: it returns the full text of an article, in Markdown, along with metadata. An agent can distinguish this from siblings like buscar_artigos or artigos_recentes because it is a single-article fetch, though the description never names those alternatives explicitly.

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?

Usage is only implied: an agent infers this is the tool to call once it already has an article identifier and needs the complete content rather than a list or search result. There is no explicit when-to-use or when-not-to-use statement, and no mention of what to do if the article is not found.

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 and a closed world, so the safety profile is covered. The description adds value beyond them by specifying the shape of each returned entry (identifier, name, article count), which matters because there is no output schema. It does not state ordering or whether the list is complete.

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?

A single front-loaded sentence naming the resource and then the returned fields, with no filler. Nothing in it is redundant with the name or title.

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 parameterless, read-only listing tool with no output schema, the description covers what it returns and the annotations cover safety. The only gaps are ordering/result-set size and a clearer boundary against consultar_glossario.

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 tool takes no parameters, so there is nothing for the description to disambiguate; the baseline applies. The sentence does not waste effort describing inputs that do not exist.

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?

States a specific verb and resource ('Lista os assuntos do NEXO CAUSAL') and even names the fields returned (identificador, nome, número de artigos). It does not explicitly distinguish itself from the closest sibling, consultar_glossario, which could also be read as a terminology-lookup tool, so an agent must infer the boundary.

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?

There is no when-to-use or when-not-to-use guidance and no reference to any sibling tool. The catalog-style nature of a zero-parameter list implies a discovery role, but that is inference rather than stated guidance.

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