leis-mcp

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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. The description adds genuine value by disclosing the exact return payload (header metadata including 'revogada' and 'versão do texto', repository path, official link), which tells the agent what it will get back.

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 that packs the action and the return contents with no filler. Slightly dense but 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 an output schema present and full parameter coverage, the description need only frame the tool's role, which it does. The return-value enumeration is mildly redundant with the output schema but harmless, and nothing an agent needs to call it correctly is missing.

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 every parameter (uf, ano, tipo, esfera, limite, numero, referencia) is already documented in the schema. The description adds no parameter-level meaning beyond that, so the 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?

States a specific verb ('Localiza') and resource ('uma norma') and enumerates what is returned (cabeçalho metadata, repository path, official source link). It is clearly distinct from ler_artigo and buscar_texto by implication, though it never names the siblings to sharpen 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?

Usage is only implied by the verb 'Localiza' and the returned metadata; there is no explicit statement of when to prefer this over listar_normas or buscar_texto, nor guidance on choosing between the 'referencia' and 'numero' lookup paths.

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 openWorldHint, so safety and idempotency are covered. The description adds the cache vs. on-demand scope distinction and the fact that results are annotated with the article number, but omits behavioral traits like accent/case normalization and the on-demand download side effect (which the schema, not the description, carries).

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 sentence with the scope ('dentro de uma norma, ou nas normas já em cache local') front-loaded before the result-shape clause. No filler, nothing repeated from the schema.

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 7 documented parameters, annotations and an output schema, the description only needs to convey purpose and scope, which it does. The remaining gap is the absence of any sibling routing or pagination/limit expectation, minor given the structured metadata.

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 every parameter (uf, ano, tipo, norma, esfera, limite, consulta) is already documented with its filter semantics and defaults. The description contributes no additional parameter meaning such as filter combination behavior or how empty filters interact, making the baseline 3 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 names a specific verb (busca) and resource (um termo dentro de uma norma / nas normas em cache), and adds the output shape (indica o artigo de cada ocorrência). That distinguishes it reasonably from buscar_norma and listar_normas, but it never names a sibling explicitly, so differentiation is inferred rather than stated.

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 'dentro de uma norma, ou nas normas já em cache local' implicitly tells the agent there are two modes (targeted vs. cache-only), which is useful context. However, there is no explicit when-to-use guidance and no routing against buscar_norma or ler_artigo for overlapping intent.

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 the safety profile (readOnly, idempotent, openWorld), and the description adds genuinely new behavioral context: results include the caput as context, a source link, and warnings when the text is revoked or not yet compiled. The missing piece is failure behavior (what happens for a nonexistent article or ambiguous norma), but the added warnings materially change how an agent should interpret output.

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 sentence that front-loads the core action and packs scope, hierarchy, and return context without waste. No preamble, no restatement of the tool name.

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 6 parameters, 100% schema coverage, an output schema, and readOnly/idempotent annotations, the description covers purpose plus the notable return traits (caput context, source link, revocation/uncompiled warnings). It falls short only on error/ambiguity behavior and on routing guidance relative to the three sibling tools.

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 property descriptions are already rich (norma accepts '8245/1991', 'CDC', 'CF', repository path; inciso accepts roman or numeral; bloco covers numbering restarts like ADCT). The description only echoes the hierarchy ('artigo, parágrafo, inciso, alínea') without adding format or composition rules, 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?

States a specific verb ('Devolve o texto exato') and resource (artigo, with paragraph/inciso/alinea granularity), plus what accompanies it (caput context, source link, revocation warnings). It is clear what the tool does, but it never contrasts itself with siblings like buscar_texto or buscar_norma, so an agent must infer whether this is a lookup by exact article or a search.

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 description's emphasis on 'texto exato' plus the artigo/paragrafo/inciso/alinea hierarchy signals it is for fetching one known provision, not for searching. There is no explicit when-to-use/when-not or pointer to buscar_texto for discovery, which is exactly the distinction an agent needs most here.

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 openWorldHint, so the safety profile is covered. The description adds genuine value beyond them by disclosing that the RESPONSE SHAPE changes with the parameters (counts vs. a listed set), which is the single most important behavioral fact for this 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?

A single front-loaded sentence that conveys the entire drill-down contract with zero filler. Nothing could be removed without losing meaning.

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?

An output schema exists and annotations cover safety, so the description's main job is the drill-down logic, which it delivers. The remaining gap is that the uf/orgao/municipio filters and pagination are never mentioned in prose, leaving the agent to discover them from the schema alone.

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, but the description goes further by explaining the conditional semantics of esfera/tipo/ano — that each successive filter changes what is returned. It says nothing about uf, orgao, municipio, limite or offset, which the schema covers on its own.

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 ('Navega pelo acervo') and precisely describes the drill-down shape of the operation (sem filtros → por esfera → por tipo → por ano → lista). This clearly separates it from search-style siblings like buscar_norma or buscar_texto, 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?

The progressive filter chain implicitly tells the agent this is the exploratory/browse entry point that feeds the other tools, but there is no explicit 'use this when…' or 'use buscar_norma instead when…' guidance. An agent must infer the distinction from behavior alone.

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