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

Annotations already cover read-only, idempotent, non-destructive behavior, so the description wisely adds non-obvious traits instead: the 90-day retention window, the size cost of full=true, and the exclusion that agent free text is absent from public files. That last note is exactly the kind of caveat an agent cannot infer from structured fields.

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-loads the action, then retention, then default output contents, then the input alternatives, then the full=true cost warning, then the exclusion. The enumeration of summary fields is not filler because there is no output schema to carry it.

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?

With no output schema, the description supplies the return-value shape (winner, time, builds, rating change, pilot stats), the size trade-off for full=true, retention limits, and an explicit data-availability exclusion. Nothing an agent needs in order to call it correctly and anticipate the result 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% and the schema already documents full, matchId, callsign, pass and pilotKey in detail. The description adds only the fallback nuance (no matchId means latest; a live pass also works) and otherwise restates what the schema carries, so baseline 3 applies.

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 ('Read a finished match') and immediately scopes it to replay files retained 90 days. It also implies its relationship to get_logbook by naming it as the source of matchId, so an agent can tell which sibling produces ids and which consumes them.

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 selection rules: pass matchId, or callsign for the latest match, and explicitly advises reading the summary before requesting full=true because the file is large. It lacks an explicit when-not clause (e.g., for in-progress matches, where act/next_report would apply), but the context is otherwise unambiguous.

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