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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description's genuinely additive detail is the '(Cost: 20 credits)' disclosure, which an agent cannot get from structured fields and which matters for call budgeting. It adds nothing further about language support breadth, rate limits, or failure behavior.

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?

Three short sentences is an appropriate size and the cost note is usefully placed at the end. However the opening is wasteful: 'Antonym Finder: Antonym Finder is an antonym lookup API' repeats the tool name twice before saying anything substantive, delaying the actual information.

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 simple two-parameter lookup with full schema coverage, an output schema, and safety annotations, the description is adequate — the core operation and credit cost are covered. What's missing is context that only prose can supply: which languages are actually supported (it says 'supported languages' without listing any) and how this differs from the near-identical WordOpposites sibling.

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% — both 'word' and 'language' (including the English default) are documented in the schema with examples. The description's 'any term and an optional language code' restates that without adding format, casing, or multi-word handling rules. Baseline 3 is the correct ceiling here.

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: 'an antonym lookup API that finds words with opposite meanings', plus a note about returning parts of speech across languages. That is clear enough to understand the operation without opening the schema. It stops short of a 5 because it never distinguishes itself from the very similarly named sibling WordOpposites, nor from Thesaurus or Dictionary.

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?

The only guidance is mechanical input advice ('Pass any term and an optional language code'), which restates the parameter contract rather than saying when to pick this tool over WordOpposites or Thesaurus. There are no exclusions, no prerequisites, and no mention of what to do when a word has no listed antonyms.

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