Update a project

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

Annotations only declare readOnlyHint=false and destructiveHint=false, both generic; the description adds the critical behavioral facts — that allowedOrigins REPLACES rather than merges the list, how to format the values, and the required project.write grant. Disclosing overwrite semantics that could silently drop origins is exactly the context annotations cannot carry.

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?

Front-loaded with the purpose, then the merge rule, then the high-risk allowedOrigins caveat — a sensible order with no filler. The sentence explaining what origins control is useful but slightly expendable, keeping it out of 5 territory.

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 6-parameter mutation tool with no output schema and half the parameters undocumented, the description still covers purpose, merge behavior, the risky field, and auth. Minor gaps remain: it never says null clears name/description, nor how errors on the required projectId are surfaced, but nothing essential to a correct call is missing.

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?

With only 50% schema coverage, the description compensates well for the most dangerous parameter, giving format, example values, an explicit "pass every origin" rule, and a note that it governs browser use of the project key. It adds little for websiteUrl vs websiteName, though the schema already annotates websiteUrl as display-only.

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 (Change) plus the resource (a project) and enumerates the mutable fields (name, description, website, allowed origins). An agent can distinguish it from create_project and get_project without opening any schema.

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?

"Only the fields passed change" establishes partial-update semantics and "Requires the project.write grant" gives a precondition, which is clear usage context. It does not explicitly name a sibling alternative or a when-not-to-use case, so it stops short of a 5.

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