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

Goes well beyond the annotations: states the required scope (applications:write), that the report is unverified, that only the 'applied' outcome advances the tracker, and that request_id must be reused to make retries idempotent. The annotations already cover side-effect safety, and the description adds the auth and idempotency mechanics an agent needs.

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?

Four compact sentences, each doing distinct work: purpose, permission, outcome semantics, idempotency, and negative scope. The most decision-relevant content (what it records and what it does not) is front-loaded.

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 5-param mutation with no output schema and no annotation-supplied behavior, the description covers auth, idempotency, outcome effect, and negative scope well. The remaining gap is the meaning of reference and submitted_at and what happens on a rejected or duplicate report.

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 full burden and it only partially compensates: it explains the semantics of request_id (retry key) and outcome (only 'applied' moves the tracker). It says nothing about application_id, reference, or submitted_at, leaving three of five parameters undocumented.

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 ('Record an ... external outcome') and immediately scopes it as an *agent-reported* record. It also draws a sharp boundary against the sibling prepare_application by declaring 'Does not submit an application or verify evidence,' so an agent can distinguish it without opening the schema.

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 clear context (this is for reporting an outcome that happened externally, not for submitting) and an explicit retry rule ('Reuse the same request_id for retries'). It never names the alternative tool to use for actually submitting an application, so routing guidance is implied rather than explicit.

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