list_documents

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

Annotations only cover readOnly/openWorld, but the description adds substantial behavioral context: the meaning of each tier value, the warning that unchecked/checked numbers should be verified against the source page, that not-loaded documents have no available text, and that results are capped at `limit` with a `truncated` flag.

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?

Front-loaded with the resource and its attributes, then filters, then return shape. Dense parenthetical asides and semicolon chains make it slightly hard to scan, but nearly every clause carries information the agent needs.

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 supplies the return contract ('{"count", "documents"}', at most `limit`, plus `truncated`), the reliability caveats on tier, and the not-loaded semantics. An agent has everything needed to call and interpret this 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 0%, so the description carries the full burden and does so: it documents family values, doc_type examples, discipline codes ('E-32', 'Q-70', 'NASA-5000') or names, query semantics, include_not_loaded behavior, and limit. Case-insensitivity is disclosed, which the schema does not express.

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 ('List the standards currently loaded') and enumerates the concrete attributes returned (issue, title, family, doc_type, discipline, record counts, tier), so the agent knows exactly what this catalog view yields. This is clearly distinguishable from retrieval siblings like get_requirement or search_requirements.

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?

Gives explicit when-to-use guidance for every filter, tells the agent when to set include_not_loaded, and adds a hard constraint: 'never answer from them, but you may name one as the standard that would cover a question.' That is a genuine usage rule, not an implied one.

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