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

Annotations already cover read-only and non-destructive hints, but the description adds substantial behavioral detail: returns one match per (file, page) with occurrence count and snippet, scans both chunk indexes, notes the two chunkings differ, and explicitly excludes the synthetic contextual enrichment from scanning. This goes well beyond the annotations and is fully consistent with them.

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 multi-sentence but front-loads the core purpose and then layers usage guidance, return behavior, and scanning scope. Every sentence contributes value; however, it is slightly verbose compared to the minimal requirement. Efficient but not ultra-tight.

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 (sibling tools, two chunk indexes, synthetic exclusion) and that an output schema exists, the description is complete. It covers purpose, when to use, return format, scanning scope, and how to follow up with `fetch`. Nothing an agent needs to call it correctly is missing.

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 each parameter is already well-documented in the input schema. The description does not add parameter-specific semantics beyond the schema; it mentions examples of what to search for, but those are illustrative of purpose, not 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?

Description states a specific verb ('Find literal occurrences') with a clear resource ('exact string in the corpus') and provides concrete examples. It explicitly differentiates from semantic `search` by stating 'use this when you need the exact string, not the concept.' This fully distinguishes the tool from siblings.

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 names the alternative `search` explicitly and gives the selection condition ('when you need the exact string, not the concept'). It also directs the agent to `fetch` for full-page reads, providing clear context and an alternative action. No gaps.

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