search

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful context beyond that: it scans the entire file (implying cost on large binaries), paginates, and formats each hit as a `function: va ...` row. Missing only rate/limit behavior or how results are ordered.

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?

A single dense sentence front-loads the verb and scope, then mode, then output format, then the exclusion. No filler and nothing an agent needs is buried.

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?

Five parameters are fully covered by the schema, and although there is no output schema the description explains the row format and paging, which fills that gap. The sibling exclusion completes the picture for correct selection.

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 kind, limit, offset, count_only and query are already fully documented with defaults and enum values. The description only restates the wildcard syntax and kind=text mode already in the schema, so baseline 3 applies.

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?

Names a specific operation (byte search) with its two modes (hex with ?? wildcards, text via kind=text), states the scope ('every byte of the file') and the output shape ('function: va ...' rows, paged). An agent can distinguish it immediately from strings, hexdump, or query without opening the schema.

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?

Provides an explicit exclusion plus the alternative: 'Not for listing strings (use strings).' That is a clear when-not with a named sibling. It stops short of stating positively when this tool is preferred over hexdump/find_crypto_constants, so not a full 5.

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