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

Annotations only say readOnlyHint=false, destructiveHint=false, idempotentHint=false. The description adds far more: sources with paid/stored credentials are skipped and reported as skipped_paid, no version is sealed, the run ends cancelled with cancel_reason preflight_complete and a preflight_report, and crucially that this cancellation is success, not a cancel. This is high-value behavioral context an agent could not infer from annotations.

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 and front-loaded, with the core behavior stated first and the surprising success-as-cancellation caveat prominent. It is one long run-on paragraph and could be broken into clearer clauses, but nearly every sentence 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 complex, non-idempotent preflight tool with no output schema and 0% schema description coverage, the description covers inputs, bounds, skip behavior, the return (run receipt), how to monitor it, and how to interpret the terminal state. Nothing essential for correct invocation 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 description coverage is 0%, so the description must carry parameter meaning, and it supplies defaults and caps for the optional bounds (max_pages_per_source default 1 max 5, max_upstream_rows default 25) plus an example showing recipe_id and recipe_digest usage. It omits the schema's 1000-row ceiling for max_upstream_rows and does not explain the recipe_digest format, so it is strong but not complete.

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 ("Starts a recipe preflight: a bounded rehearsal of a full run") and immediately scopes it as a bounded, non-live rehearsal. It distinguishes itself from the sibling start_run by describing exactly what it does and does not do (never seals a version, never becomes live).

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?

Explicitly names alternatives and the conditions that select them: watch with run_events or get_run, then start_run once the report is clean, using full mode unless a bounded sample was requested. It also gives a remediation loop (fix what the report names, register again, test again).

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