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

The description adds significant behavioral detail beyond the readOnlyHint and idempotentHint annotations: it defines the exact confidence tiers (exact, strong, ambiguous), explains how ambiguity is flagged, and discloses the special handling for citations to instruments outside the corpus (named with CELEX and ELI rather than guessed at). This is rich, concrete behavioral information that helps the agent anticipate outputs.

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 front-loaded with the core question, then provides dense, useful detail about output categories and out-of-corpus behavior. It contains no fluff and every sentence adds meaning, though it could be slightly better structured as a list for scannability.

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 description covers the tool's core behavior, confidence levels, and edge-case handling, while annotations cover side-effect safety and an output schema exists. The main gap is the absence of guidance around limit/cursor pagination and explicit routing among sibling tools, but the essential invocation context is present.

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 33%, with citeration fully documented in the schema but limit and cursor left undocumented. The tool description also does not explain limit or cursor semantics or how they affect candidate ranking or pagination. Since the description does not compensate for the low schema coverage, parameter semantics are under-specified.

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 identifies the tool as a citation resolver: it explains what question the tool answers ('What does this citation refer to?') and specifies the output as ranked candidates with confidence classifications. This distinguishes it from sibling tools like get_instrument or get_provision, which imply direct retrieval rather than candidate ranking and ambiguity resolution.

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 context by emphasizing that the input is 'a citation in any form a reader would write', but it does not explicitly state when to prefer this tool over alternatives like search_legislation or get_instrument. It provides no exclusions or when-not guidance, so the agent must infer the appropriate use case from the description alone.

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