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

Annotations already cover readOnly and openWorld, but the description adds genuinely non-obvious behavior: the payload excludes attachment files and guideline page bodies, and it warns against triggering case creation via next_action after a mere view. It never explains what refresh=true does, which is the one behavioral gap for a read tool that may re-fetch external data.

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?

Return fields are front-loaded in the first sentence, followed by exclusion scope and a workflow caution, with no filler. The document_handoff/next_action sentences are slightly off-topic for a pure detail-read tool but earn their place as behavioral warnings.

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 enumerating return values is a bonus rather than a necessity, and scope exclusions are well covered. However, for a 2-parameter tool at 0% schema coverage, leaving refresh completely undocumented makes the definition incomplete for correct invocation.

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 must carry parameter meaning and it does not: subsidy_id is never described (format, where it comes from) and refresh is not mentioned at all despite being a non-obvious flag that likely changes fetch behavior. The tool relies entirely on the caller inferring both parameters.

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 opens with a specific verb and enumerates the fields returned (detail_text, rounds, deadline, amount, official link, attachment names/page counts), so the resource is unambiguous. It does not explicitly contrast with the closest sibling, search_subsidies, which is left to inference.

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?

It clearly states what is out of scope (attachment binaries, guideline body text) and names the correct alternatives, search_guideline and get_guideline_pages. The workflow caveat about confirming intent before next_action further narrows correct usage, though when to prefer this over search_subsidies is only implied.

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