spec-requirements

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

With no annotations, the description carries the full burden. It does disclose one genuinely important behavioral trait - that re-saving removes downstream approvals, a destructive side effect. Beyond that warning it says nothing about permissions, reversibility, or state, but no return format is needed since an output schema exists.

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 short sentences with no filler, and the destructive warning is front-loaded right after the core purpose. Efficient, though the brevity borders on under-specification rather than tight conciseness.

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?

An output schema covers return values, but with zero annotations and 0% parameter coverage, the description is too thin for a read/write tool that alters approval state. It omits the parameter trigger, permission expectations, and any sibling routing.

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 coverage is 0%, so the two parameters (content, feature_name) are wholly undocumented. The description hints at content's read/write role through 'lê ou salva' but never names content or feature_name or explains the null/default convention, leaving the semantics largely to inference.

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?

States a specific verb pair (reads or saves) and a specific resource (requirements.md), which is enough to identify the operation. It does not differentiate itself from siblings like spec-init, spec-design, or spec-approve, but the resource target is unambiguous.

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 dual read/write behavior is implied but the trigger condition is never stated - an agent must infer that passing content means save and omitting it means read. No mention of when to prefer this tool over spec-init or spec-design, and no prerequisites.

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