source_security_review

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

With no annotations, the description carries full burden; it does useful work by disclosing that output is heuristic and 'never confirmed automatically', which sets the reliability bar. It omits whether the tool is read-only, whether it processes content inline versus fetching a file, any size or cost limits, and what the leads look like.

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?

Two compact sentences, front-loaded with the action and followed by the caveat about result reliability; no wasted wording. The terseness costs a little, since 'Phase 2/3' is undefined jargon.

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?

No output schema and no annotations means the description should explain the input format, the shape of returned candidates, and the phase semantics; it does none of these. For a tool whose only real job is transforming a source blob into leads, the missing input/output contract is a significant gap.

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 0% for two parameters, and the description adds nothing about them. Critically, it never clarifies whether 'source' is raw source-code text (max 100000 chars suggests inline) or a path/identifier, nor what 'filename' is used for — this ambiguity can cause a failed invocation.

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 gives a specific verb and resource — 'generate heuristic source-review candidates' — plus a workflow anchor ('Phase 2/3'). It does not name any sibling tool, so the agent must infer that repository_read_file / repository_inspect are the alternatives that feed this step.

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?

'Phase 2/3' implies pipeline placement, but the description never states when to call this versus repository_inspect, repository_read_file, or the audit_* validators. There are no explicit exclusions or prerequisites, so usage is only implied.

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