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

Annotations provide readOnlyHint=true, so safety is clear. Description adds deep behavioral context: denominator contract, interpretation of 'win' vs 'partials', that 'wins/total is not a win rate', null handling for win_rate when settled=0. No contradiction with annotations. Description adds substantial value beyond 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?

Description is somewhat long but every sentence earns its place. Front-loaded with purpose and scope. The detailed behavioral notes are justified given the tool's complexity. Minor verbosity in the denominator contract explanation but not excessive.

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 read-only tool with output schema and one optional parameter, description covers all necessary context: what it does, what it doesn't do, how to interpret output fields, and alternative tool. No gaps. Output schema handles return values.

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 has 1 param (days) with 0% description coverage. Description explains valid range (1-365) and default (30), which adds meaning. Could be more explicit about parameter name in text but the context makes it clear.

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?

Description uses specific verb 'backtest' and resource 'performance' with scope 'over last N days'. It distinguishes from sibling tool get_proof by stating its different purpose. No ambiguity.

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 states when to use: 'no asset filter — performance is aggregated across all assets'. Explicitly states when not to use: 'For the gated per-type verdict ... use get_proof instead'. Also mentions data source equivalence to REST endpoint. Provides clear context for selection.

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