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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds valuable context beyond these: it charges $2 per call, performs verification against the issuing provider 'where supported', and implies an external network interaction (openWorldHint is reinforced). No contradictions exist. It does not mention rate limits or output format, but for a read-only scan this is adequate.

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 two sentences, front-loaded with the action and scope. The cost note is a single brief clause. Every word adds value; no fluff.

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 nested source object, a boolean flag, and a chaining ID, the description covers the core purpose but not the full parameter semantics. No output schema exists, and the description does not hint at what the result contains (e.g., findings list, verification status). The include_history parameter is not explained in either the description or schema, and the source object's field constraints are left vague. While the schema documents previous_scan_id, overall the context is incomplete for an agent to invoke with full confidence.

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 33% (only previous_scan_id documented). The description helps interpret the 'source' parameter by naming the two modes (source code or git repo), which aligns with the schema's type enum. However, it does not explain the structure of source (when to use url vs code), nor the meaning of include_history. The description partially compensates but leaves gaps.

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 the tool's function: 'Detect hardcoded credentials, API keys and tokens in source code or an https git repo.' It includes the specific engine (trufflehog) and verification behavior, and explicitly frames the use case as 'did we commit a secret'. This distinguishes it from siblings like sast_scan or credential_check.

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 provides a clear usage context: 'Use when the question is "did we commit a secret".' It also notes the cost, which is a practical consideration for deciding when to invoke. However, it does not explicitly list alternative tools or when to avoid use, so it stops short of full alternative guidance.

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