verify_index

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

Beyond the annotation readOnlyHint=true, the description discloses detailed behavior: byte-offset reading, SHA-256 recomputation, the meaning of a clean cache result (internal consistency only, not source currency), and that live mode reports drift/missing/error counts and drifting section IDs. This is rich, non-contradictory context.

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?

Every sentence earns its place. The description is front-loaded with the core identity, then detail on modes, output, and sampling. It is information-dense without 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 (two verification modes, SHA-256 recomputation, output reporting), the description covers all necessary aspects: algorithm, mode semantics, output contents, and optional sampling. No output schema exists, so the description appropriately explains return values.

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 67% (repo lacks a description), but the description compensates by explaining the source enum values in depth ('cache' vs 'live') and the purpose of the sample arg ('cheap CI checks'). It adds meaning beyond the bare schema, especially for source and sample.

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 ('Byte-offset integrity check') and clearly explains what it does: walks sections, byte-range-reads bytes, recomputes SHA-256, and compares to stored content_hash. This distinguishes it from sibling tools like get_doc_health or check_embedding_drift.

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 gives explicit guidance on when to use source='cache' vs source='live', including what each result does and does not prove. It also mentions using the sample arg for CI checks. However, it does not directly compare to alternative tools like check_embedding_drift or get_index_overview, so it lacks explicit exclusion guidance.

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