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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds substantial context beyond them: no history/no restore path, the `deleted: false` response when the key is absent, and an authorization-refused case for the reserved `config` key. That is exactly the extra behavioral detail an agent needs before firing an irreversible call.

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?

Four short sentences, zero boilerplate, with the irreversible nature and the reserved-key guard both front-loaded before the edge-case response behavior. Every sentence carries distinct information.

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?

There is no output schema, yet the description still explains the meaningful response signal (`deleted: false`), the irreversibility, the authorization refusal case, and the reserved key. Combined with annotations and full schema coverage, an agent has everything required to call this safely.

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 100%, so the baseline is 3, but the description adds meaning the schema lacks: the `key` value `config` is reserved and deletion of it is refused whatever the role. `expectedProjectId` is left entirely to the schema, which handles it well.

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 (PERMANENTLY deletes) and a precisely scoped resource (a CUSTOM project metadata entry), explicitly excluding the reserved `config` entry. This lets an agent distinguish it from delete_project, set_project_metadata, and get_project_metadata 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?

It gives real preconditions — only custom entries are deletable, `config` is refused regardless of role — which tells the agent when the call will and won't work. However it never names an alternative tool (e.g. set_project_metadata for overwriting, get_project_metadata for reading first) or states when deletion is the right choice over updating a value.

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