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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the tool is known to be safe. The description adds significant behavioral context: it describes the structured diff (added, removed, modified text), the 'Sources used' audit table with zero-result note, and meta.render_contract for reproducing source attributions. This goes well beyond what annotations provide and gives the agent a clear picture of the output and its provenance.

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 three sentences, each earning its place: the first states the core function, the second provides usage triggers with examples, and the third details the output format including the audit table and meta contract. It is front-loaded with the primary purpose and contains no fluff or repetition of schema content.

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?

There is no output schema, so the description compensates by thoroughly explaining the return value: a structured diff with added/removed/modified text, a 'Sources used' section, and meta.render_contract. Combined with the exhaustive parameter schema and safety annotations, the agent has all necessary information to invoke the tool correctly and interpret results. The mention of zero-result note also handles an edge case.

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?

The input schema covers all 5 parameters with descriptions (100% coverage), so the baseline is 3. The tool description does not elaborate on parameter details further, but it implicitly reinforces semantics through example queries ('DORA amendment', 'GDPR Article 17'). Since the schema already explains parameters clearly and the description adds minimal extra meaning, a 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 opens with a specific verb+resource: 'Compare two versions of a legal provision to see what changed.' It distinguishes the tool from siblings like get_provision or search by focusing on the diffing use case, reinforced with concrete example queries ('what changed in the latest DORA amendment', 'differences in GDPR Article 17 after the update'). This fully clarifies the tool's purpose.

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 states 'Use this when...' followed by three representative user requests, giving clear context for when the tool is appropriate. It does not name alternatives or provide when-not guidance, but the usage scenarios are specific enough to differentiate from sibling tools. A missing explicit exclusion keeps it from a 5.

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