verify_quotes

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

With no annotations provided, the description carries full burden. It discloses that the tool is local-text only, does not make outbound requests, and returns specific results (present, absent, missing_source_text). It covers key behaviors sufficiently, though it could mention if there are any side effects or error conditions.

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 description is two sentences plus a clear list of non-capabilities. It is front-loaded with the purpose and every sentence adds value. No unnecessary words.

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?

Given 2 parameters (one optional, one nested object) and no output schema, the description fully explains inputs, outputs, and limitations. It provides complete guidance for an agent to use the tool correctly.

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 100%, so baseline is 3. The description adds value beyond schema by clarifying that 'texts' maps evidence_id to plain text and explaining that both 'pack_json' and 'texts' are expected inputs. It also describes the structure of 'pack_json' as containing evidence IDs and quote fragments.

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 clearly states the tool checks whether quoted fragments from an evidence pack appear in caller-provided source text. It uses specific verbs ('Check') and resources ('quoted fragments from an evidence pack'), and distinguishes from siblings by listing what it does not do (no outbound requests, fact-checking, etc.).

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 description explicitly says 'Use when you have local excerpts and need to catch citation drift or misquoted snippets.' It also lists limitations (local-text only, no outbound requests, etc.), which helps agents decide when not to use. However, it does not directly name alternative sibling tools like 'audit_claims' or 'validate_evidence' for other purposes.

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