search_notices

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: it operates on a cache and an empty result is not authoritative proof of absence. That staleness caveat is exactly the kind of thing annotations cannot express.

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 clauses, front-loaded with what the tool does, then the caveat, then the workflow. Every clause carries information; nothing is padded.

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, so return values need not be described, and the cache caveat plus workflow advice is useful. However, with 0% parameter documentation the agent still cannot tell how to shape a call, leaving a real gap for a 4-parameter search 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% across 4 parameters (limit, query, offset, source), and the description says nothing about them. It mentions 'scope' and 'body' abstractly but never explains what query matches, what source values are valid, or how limit/offset page the results. It fails to compensate for the coverage gap.

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+resource: search the local notice cache. It also implicitly distinguishes itself from siblings by naming the refresh-then-read workflow. Not a 5 because it never contrasts itself with get_notice or other retrieval tools by name.

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 actionable ordering guidance: refresh by scope first, then read the body to confirm. This maps onto the sibling tools refresh_source and get_notice. No explicit 'do not use this for X' exclusion, so it falls short of a 5.

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