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

Goes well beyond the destructive/non-idempotent annotations: states approve cannot be undone, reject sends nothing, cancel only works while queued/preparing, and that a re-submitted approve reports as already approved. Error-recovery behavior and the 25-id batch cap are disclosed, which the annotation set does not cover.

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-loaded with the action list and densely packed with zero filler, but the heavy use of inline quoted fragments and parentheticals makes it read as a run-on string rather than cleanly structured sections. Every sentence still earns its place.

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 destructive, multi-mode, open-world tool this covers preconditions (explicit user go-ahead), per-decision parameter requirements, error/timeout recovery, sibling alternatives, and the natural next step. With an output schema present, the description needn't explain return values, and nothing an agent needs to invoke it correctly 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 the schema already defines each field; the description adds genuine conditional semantics by mapping which parameters each decision requires (refine needs document_type + instructions, set_stage needs stage, approve/reject/cancel need nothing else, re_prepare takes optional steps). It doesn't add format details for instructions beyond the schema's 2,000-char cap, so not a full 5.

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?

Names a specific resource (the user's applications) and enumerates every action via the decision enum (approve/reject/cancel/refine/re_prepare/set_stage), each with a one-line effect. It also explicitly distinguishes itself from siblings getmattered_apply and getmattered_triage_matches 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?

Explicit when-to-use rules: approve only on the user's explicit go-ahead; do not use for matches with no application yet (use apply/triage_matches); on timeout or error call getmattered_get_applications before retrying; follow up with getmattered_get_applications. Alternatives and exclusions are named, not inferred.

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