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

Annotations cover the safety profile (non-destructive, idempotent), and the description adds material context beyond them: case-insensitive matching, dedupe semantics on re-send, the shape of the response (saved state of every term, new or pre-existing), and that the operation is free with no credit cost.

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 trigger condition, then dedupe behavior, then cost, then the anti-pattern routing. Each sentence carries distinct information with no restatement of the name or schema.

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 single-parameter mutation with an output schema and full schema coverage, the description supplies the trigger, the alternate tool, idempotence behavior, and cost implications. Nothing an agent needs to call it correctly 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 100%, so the baseline applies; the schema already documents term length limits, the optional urls array, and the 50-item cap. The description adds only indirect meaning by explaining that re-sent terms return the stored record, and says nothing specific about the urls sub-field.

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 (save/add) and resource (organization's Saved Keywords list in Tailwind), and explicitly distinguishes itself from list_saved_keywords. An agent can identify the operation 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?

Gives both trigger conditions ('when the user asks to save, add, or track keywords, or agrees to add terms you suggested') and an explicit exclusion naming the sibling tool to use instead for lookups. Nothing is left to inference.

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