Search Code

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint. The description adds valuable behavioral context: it is a regex search that is bounded, returns context lines, and redacts secrets. This extends beyond annotations without contradicting them. Missing are details on performance or path restrictions.

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 sentence, concise and front-loaded with key action and features. Every word serves a purpose, no filler.

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?

While the description covers core functionality, it lacks details on parameter interplay, performance implications of bounds, or how path resolution works. With 8 parameters and an output schema, more context would improve completeness, but existing input schema and annotations provide some scaffolding.

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 25% (only path and filePattern have descriptions). The description does not explain the primary parameter 'pattern' or other critical ones like 'redactSecrets', 'maxFiles', 'maxResults'. Given low coverage, the description fails to compensate by clarifying parameter semantics.

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 it performs a 'bounded regex search across repository text files' with 'context lines and secret redaction'. This specifies the verb (search), resource (text files), and unique features, distinguishing it from siblings like sdlc_secret_scan which focuses on secret detection only.

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?

No explicit guidance on when to use this tool vs alternatives such as sdlc_secret_scan or sdlc_read_file. While the description mentions 'bounded' and 'secret redaction', it does not clarify when a simpler search would suffice or when to prefer other tools for secret scanning.

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