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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes well beyond by disclosing idempotent collapse of retried reports, the 'never guess / send null with source "unknown"' rule, mandatory redaction of keys/tokens/emails/wallet secrets, the currently-mandatory summary field, and that the endpoint is unauthenticated.

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?

Dense but mostly front-loaded: the purpose and cadence come first, followed by mechanics and constraints. Sentences are long and occasionally cram multiple rules, but nearly every clause carries actionable contract detail rather than filler.

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 complex 20-param, 5-required write tool with no output schema, the description covers the contract semantics, idempotency, submission cadence, redaction, and auth. It does not describe the response or failure modes of the call itself, which is the main remaining gap.

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?

With 50% schema description coverage and 20 params, the description compensates substantially: how to generate sessionId (UUID v4, once per attempt), how seq increments, that phases roll-up belongs only on phase 'session', and that unknown phase/outcome/harness values are stored as other/unknown. It still leaves fields like env, ids, logs, pack, device, and proposal unexplained beyond the schema.

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: 'Report one phase of an onboarding attempt, success or failure,' naming the contract version. It is scoped clearly enough to separate from generic siblings, though it never explicitly contrasts itself with the near-named sibling pcc_report, leaving that differentiation 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?

Gives explicit trigger conditions: 'Send one report when each runbook phase ends, and a final report with phase "session"... also when you stop early (outcome abandoned or budget_stop).' It also states the idempotency rule (same sessionId and seq collapses) that governs whether to resend.

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