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

With no annotations provided, the description carries the full disclosure burden and does so richly. It reveals that this is heuristic text analysis, not a parser or type checker, explains that some checks operate across the whole file set, and discloses potential false confidence from keyword matching. It also explains file-scope vs project-scope findings and gives severity guidance.

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 long but every sentence adds necessary information, and it is well structured: purpose, usage constraints, finding types with concrete examples, and limitations. The use of bullets and short labels keeps dense content scannable, and the most important operational guidance is front-loaded.

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 no annotations and no output schema, the description compensates by explaining what findings look like, providing examples of both scopes, warning about limitations, and telling the agent how to interpret error vs needs_review results. It is complete enough for an agent to invoke the tool correctly and act on its results.

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?

The schema already documents the `files` parameter well, and the description adds essential behavioral semantics beyond it: passing every auth/session-related file in one call matters because some checks are evaluated across the whole set. It also clarifies that project-scope findings depend on what was passed in, which directly informs how an agent should construct the parameter.

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 a specific action and resource: 'Checks source you already generated against the secureFlows integration rules.' It distinguishes this static lint tool from sibling auth/session and URL-building tools by emphasizing that it scans code rather than performing session operations.

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 gives explicit when-to-use guidance: no secureFlows token needed, safe at scaffolding time, and all auth/session-related files should be passed in one call. It also states clear exclusions: not a substitute for the Agent implementation checklist and not for checks needing a running app.

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