award_progress

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 real behavioral substance: prefecture returns both obtained and un-obtained, jcc/gridsquare return only a worked list plus count, qsl_rcvd narrows judgement to QSL-received contacts, and include_worked_detail attaches counts and first/last dates.

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-loads the core effect in one line, then progressively layers kind-specific caveats and the argument list. Slightly long and the Args block partly restates schema fields, but every sentence carries information.

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?

No output schema exists, and the description compensates by explaining what each kind returns (obtained/un-obtained vs list+count) and what include_worked_detail adds. Adequate for a 7-parameter read tool; only the concrete response shape per kind is left implicit.

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 burden and largely meets it: it documents all seven parameters, including the kind enum values (prefecture/jcc/gridsquare), band/mode filters, date range format (YYYY-MM-DD), and the effect of qsl_rcvd and include_worked_detail. Minor gaps remain (e.g. accepted band/mode value forms).

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 (アワードの進捗を出す) and immediately scopes the return to obtained + un-obtained items. It further distinguishes its own behavior per kind (prefecture vs jcc/gridsquare), which lets an agent tell it apart from siblings like qso_stats or search_qso.

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 concrete usage conditions: prefecture kind reveals the missing 47 so it suits 'where to aim next', while jcc/gridsquare cannot be judged against a defined population and only return a worked list and count. Clear context but no explicit naming of sibling alternatives or when-not-to-use statements.

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