Approve or Reject Applications

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

Annotations provide destructiveHint=true and idempotentHint=false, and the description richly elaborates on those: 'approve' 'spends one of their applications per job and cannot be undone', 'reject' sends and spends nothing, 'refine' 'uses AI credits', and a retried approve that already went through 'is reported as already approved'. This adds meaningful behavioral context beyond the annotations without contradicting them.

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 long but every sentence earns its place. It front-loads the core action and decision inventory, then layers constraints (id source and cap, consent rule, timeout recovery), exclusions, and the follow-up call. For a six-mode tool with error handling and sibling routing, this density is appropriate with zero fluff.

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 no prose explanation. The description covers everything needed for safe invocation: all six behaviors, the decision-to-parameter coupling, id sourcing and limits, the explicit-go-ahead consent rule, timeout/error handling, when-not-to-use with named alternatives, and the next step ('aiapplyd_get_applications to follow the submissions'). Nothing an agent needs is missing.

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 coverage is 100%, so baseline is 3, but the description adds real meaning beyond the schema: it couples decisions to their required parameters ('refine' needs document_type and instructions, 'set_stage' needs stage, 're_prepare' takes optional steps), caps application_ids at 25, and specifies that ids come from aiapplyd_get_applications. This explains the interplay between parameters that the schema's per-field descriptions do not.

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 clear verb and resource ('Act on the user's applications') and then enumerates each decision mode ('approve', 'reject', 'cancel', 'refine', 're_prepare', 'set_stage') with its specific effect. It also distinguishes itself from siblings by naming aiapplyd_apply and aiapplyd_triage_matches as the tools for matches with no application yet.

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?

Provides explicit when-to-use guidance: pass up to 25 ids 'from aiapplyd_get_applications' and only approve 'on the user's explicit go-ahead'. Explicitly states when not to use it ('Do not use it for matches with no application yet; use aiapplyd_apply or aiapplyd_triage_matches') and gives recovery guidance for timeouts and errors. This is full when/when-not/alternatives coverage.

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