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

The description adds behavioral context beyond the annotations: it discloses the owner-only restriction, the error for editors, and the partial-update behavior ('Only fields present in the patch are touched'). These are crucial details not captured by readOnlyHint/destructiveHint. No contradiction with annotations.

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 highly concise and well-structured: two sentences cover purpose, scope, error behavior, patch semantics, and alternative tool. No unnecessary words, with critical information 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?

For a mutation tool with three parameters and no output schema, the description provides comprehensive guidance: who can use it, what it does, how partial updates work, and what happens for unauthorized callers. It also names the read-only alternative. No significant gaps.

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 has 0% description coverage, so the description must compensate. It explains that only fields present in the patch are touched, which conveys that all parameters are optional and that absent fields remain unchanged. While it doesn't describe each parameter individually, the parameter names (maxKeyTtlDays, defaultKeyTtlDays, editorsMayCreateNonExpiringKeys) are self-explanatory, and the patch semantics are the key missing piece.

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: 'Edit the project's key policy' with the verb 'Edit' and specific resource. It distinguishes from the sibling get_key_policy by explicitly directing readers to that tool for reading, and adds scope ('Owner-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?

The description provides explicit usage context: 'Owner-only' and 'Editors calling this get an error — use get_key_policy to read' clearly state when to use this tool versus the alternative, and who should use it. It also specifies the patch semantics, making the intended use unambiguous.

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