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

Annotations only declare readOnlyHint and openWorldHint; the description goes far beyond by disclosing pricing and quota (25 free calls/day, then $0.01 USDC via x402), hard caps (50 quotes, 600000 characters), and the determinism guarantee ('Deterministic string matching, no model'). It also explains what each verdict means, including the negation add/drop flag, which is exactly the behavioral context an agent needs before trusting the result.

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?

The pricing bracket is front-loaded and the rest reads as a tight sequence: when to use, the category taxonomy, the negation flag, then limits. Dense but every sentence carries information; only the enumerated verdict glosses push it toward the long side for a two-parameter tool.

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 carries the burden of explaining returns, and it does: verdict labels, location via line and character offsets, and the returned source passage. Combined with the stated caps and determinism claim, an agent can call this correctly and interpret the result without further documentation.

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 50% and the description largely restates the caps already encoded as maxItems 50 and maxLength 600000 rather than adding new syntax or format guidance. The 'label' parameter on each quote object is left unexplained in both the schema and the description, so the gap is not compensated.

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?

The description states a specific verb and resource: check each claimed quote against the source text and classify the match. It enumerates the exact outcome categories (exact, same_words, numbers_differ, close_but_different, not_found), which makes it immediately distinguishable from siblings like verify_answer or text_facts that could otherwise look similar.

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?

It gives an explicit trigger: use it 'before your agent quotes, cites or summarises a document.' That is a clear usage context. What it does not do is name an alternative sibling (e.g. text_facts or verify_answer) and state when to pick that instead, so it stops short of a 5.

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