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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world behavior, and the description adds genuinely new operational facts: the exact permission and role requirements, the extra secrets:write gate for sensitive fields, and the protected-project refusal. It does not describe overwrite semantics (whether an existing value is replaced wholesale) or the response, which keeps it off a 5.

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 tight sentences, front-loaded with what the tool does and followed by the authorization constraints. No filler, no restatement of the title.

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 four-parameter mutation tool with annotations covering the safety profile and no output schema, the description covers permissions, sensitive-field handling, and a failure mode (protected projects). The remaining gap — upsert/overwrite semantics for an existing key — is minor but real.

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 50% — project and sensitive are documented in the schema, while key and value carry only length bounds. The description partially compensates by illustrating the kinds of data key/value hold and by tying 'sensitive' to the secrets:write requirement, but it adds no guidance on key naming rules or value replacement behavior.

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 pair ('create or update') plus the resource ('project key/value field') and concrete examples of what a field holds (owner contact, region, notes). It is clearly distinguishable from delete_field, though it never names a sibling to contrast with set_secret, so it stops short of a 5.

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?

It states prerequisites (projects:write, editor role, secrets:write for sensitive fields) and one exclusion (protected projects refuse sensitive writes), which is real usage context. However, it never says when to choose this over set_secret or set_field-adjacent siblings, leaving the key-vs-secret decision to inference.

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