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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses refusal behavior: 'Refuses (status: upstream_validation) if confidence is 0.0... or if a neutral citation has no resolved_url.' It also states 'no network call' and warns against manufacturing citations. This adds significant behavioral context that annotations alone do not provide.

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 front-loaded with the critical workflow instruction and is organized into short, purposeful sentences. There is some repetition ('do NOT construct the input fields yourself' and 'do not guess'), but it is a safety-critical guardrail that benefits from emphasis. Overall, every sentence earns its place, though minor tightening could remove redundancy.

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 the tool's complexity (14 parameters, multiple citation types) and the existence of an output schema, the description fully covers what an agent needs: the pipeline sequence, refusal conditions, the anti-fabrication rule, and the authoritative format. It does not explain return values, but the output schema covers that. The description is complete for its role.

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 schema fully explains each parameter. The description adds an overarching rule that all parameters must come from citations_resolve, but this is more of a usage guideline than parameter semantics. The schema already covers details like confidence refusal and the EU-retained-law raw handling, so the description adds no new per-parameter meaning. Baseline 3 is appropriate.

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: 'produce the correctly formatted OSCOLA citation string.' It also distinguishes from siblings by explicitly saying 'USE THIS TOOL AFTER citations_resolve,' placing it clearly in the pipeline relative to citations_parse and citations_resolve.

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 provides explicit when-to-use guidance: 'USE THIS TOOL AFTER citations_resolve' and 'Pass the parsed fields returned by citations_resolve directly into this tool.' It also gives strong exclusions and failure-handling instructions: 'DO NOT construct the input fields yourself,' 'surface the failure and ask the user for the source URL or better identifying details.' This is comprehensive and actionable.

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