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

With no annotations, the description does a reasonable amount of work: it names the exact return fields (warrant_url, py_url, md_url, fetch_when), gives a cost estimate (~220 tokens), and discloses a failure mode where a failed seal means the .md should not be fetched. It doesn't state whether the lookup itself is free of side effects or how candidates are ordered/ranked.

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?

Three short sentences, each with a distinct job: purpose, return shape, and procedural rule. The purpose leads and the conditional warning comes last, so nothing is buried.

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 lookup with no output schema, the description covers purpose, return fields, cost, and a follow-up rule—enough to call it correctly. The remaining gaps are conceptual: what a 'seal' is and whether candidates are ranked or exhaustive.

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 single 'symptom' parameter is fully documented in the schema at 100% coverage, including an example key format. The description adds no semantics beyond what the schema provides—nothing on key normalization, case sensitivity, or what happens for an unrecognized key. The baseline of 3 applies when the schema carries the load.

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: 'Route a runtime symptom to candidate record addresses.' An agent can tell this is a symptom-to-record router rather than a record fetcher. It does not explicitly name the sibling it contrasts with (corpusfetch_lookup_exception), relying on the word 'symptom' to imply the split.

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 gives downstream sequencing advice ('Fetch the warrant first (~220 tokens); if its seal fails, do not fetch the .md'), which is genuinely useful workflow guidance. However, it never states when to select this tool over corpusfetch_lookup_exception or when to skip lookup entirely, so the selection guidance is only implied by the tool name.

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