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

Annotations already cover readOnly, idempotent, and non-destructive, but the description adds genuinely new context: it is free, it scores on named dimensions, it never raises a protocol error and instead returns an {"error": ...} object, and retry after correction is safe. Minor repetition of the read-only/idempotent claims already in annotations keeps this from a 5.

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 verb, scope, and the FREE signal, then the scoring criteria. The embedded JSON example consumes space but is doing real work illustrating input and output; the trailing retry sentence is slightly redundant with the idempotent annotation.

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?

A complete picture for a simple single-parameter tool: purpose, alternatives, error contract, and cost. Since an output schema exists, the inline return-value example is somewhat duplicative rather than necessary, which caps the score at 4.

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?

The single parameter already has 100% schema coverage including the 'first 20' truncation, so the baseline is 3; the description goes further with a concrete input/output example showing the expected shape. It does not add per-parameter constraints beyond what the schema states.

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?

Names a specific verb and resource (score and rank email subject lines) plus scope (up to 20, best first). It explicitly contrasts itself with headline_analyzer and audit_copy, so an agent can place 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?

States when to use it ('several subject lines need ranking against deliverability and curiosity signals') and when not to ('not for article headlines... not for message bodies'), naming the alternative tool for each exclusion.

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