Search agency issuances

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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds valuable behavioral insight: 'Below confidence threshold it reports insufficient corpus coverage rather than guessing' – this tells the agent how low-confidence results are handled. It also details pagination behavior ('check hasMore/nextOffset'). Both additions go beyond annotations, but there is no mention of rate limits or auth, though those are not necessarily needed for this read-only 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 concise and well-structured. It front-loads the core purpose, then adds behavioral and pagination notes. The phrase 'BIR first, Phase 3' is a development milestone that is irrelevant to an agent and adds noise, which is a minor inefficiency. Otherwise, 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?

Given the tool has 5 parameters, an output schema, and safe annotations, the description covers the essential usage points. Pagination is explained, filters are mentioned, and the low-confidence behavior is disclosed. Since the output schema exists, not describing return values is acceptable. The description is sufficiently complete for an agent to call the tool correctly, though it could mention that the query is mandatory, but that is already in the schema.

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% – all five parameters have descriptive text in the schema. The description adds minimal extra meaning: it restates that you can filter by agency or issuanceType and mentions using offset for pagination, but these are already described in the schema. No new format or nuance is provided for the parameters, so it meets the baseline 3 but does not exceed it.

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 a specific verb and resource: 'Lexical (FTS5/BM25) search over the administrative issuance corpus'. It distinguishes from siblings such as search_statute and search_jurisprudence by specifying the corpus (administrative issuance) rather than a generic search. The added note 'Information retrieval, not legal advice' clarifies the tool's scope. However, it doesn't explicitly reference sibling tools or contrast them, so it's 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 says 'Filter by agency or issuanceType' and explains pagination, giving operational guidance. But it does not explicitly state when to use this tool versus alternatives like search_statute or search_jurisprudence. The context implies it is for administrative issuances, but no direct when-to-use/when-not-to-use guidance is provided. Sibling tools are not named, so the agent must infer the intended context.

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