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

Annotations already declare readOnlyHint=true. The description adds useful behavioral context: explains what each outcome means (corroborates, mismatch, unknown) and notes 'unknown costs nothing', which is a behavioral nuance. It doesn't describe error behavior, but the core semantics are well covered.

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 a single, front-loaded sentence that starts with the core purpose and efficiently packs in outcome definitions. Every clause contributes meaning; no filler or 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 simplicity (1 parameter, no output schema), the description fully covers what the tool does, the possible return values, and their criteria. It even notes the cost implication of 'unknown'. For a read-only tool with no output schema, this is complete.

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% (finding_id is described as 'Finding identifier'). The description adds context that the finding is the subject of per-use relevance assessment, which slightly enriches the parameter meaning. Baseline 3 is appropriate since the schema already handles documentation.

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 evaluates per-use citation relevance for a specific finding, with specific outcomes (corroborates, mismatch, unknown). It distinguishes itself from siblings by emphasizing it's per finding, not per URL. However, it doesn't explicitly name alternative tools or differentiate from 'check_citation'.

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?

Usage context is implied: 'the same URL can be cited rightly by one finding and wrongly by the next' suggests it's for when you need per-finding relevance assessment. But there is no explicit when-to-use or when-not-to-use guidance, and no mention of alternatives.

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