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

Annotations only say readOnly/no open world; the description goes far beyond them, explaining exactly how API-key scoping narrows results, the inScope/keyScope.outOfScopeHidden flags, and that a non-keyed session is unnarrowed. The warning that an absent project may still exist outside key reach is exactly the kind of caveat annotations cannot convey.

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 one-line summary, which is good, but the body is dense and format-heavy (backticks, '⚠️', parenthetical MCP-vs-chat aside) and the final paragraph about where the id is used is convoluted. Most sentences earn their place, but the same information could be delivered with tighter phrasing.

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?

With no output schema, the description compensates by enumerating returned fields (id, name, role, primaryKind, timestamps) and covering key-scope behavior and the false-negative caveat. It omits ordering and pagination behavior, which matters for a list tool that may return many projects.

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?

There are no meaningful parameters (only an '_unused' placeholder), so the baseline is 4. The description correctly adds no parameter detail and instead spends its space on scoping semantics that function like implicit inputs.

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 and resource with its scope: 'Lists the projects the authenticated user can access (owned + shared)'. It also names the return fields and ties the returned id to sibling tools (expectedProjectId, set_active_project), so an agent can place it among ~140 siblings without ambiguity.

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?

Clearly positions the tool as the discovery step: the id it returns is what set_active_project binds and what expectedProjectId takes. It does not state explicit exclusions (e.g. 'do not use to inspect a single project — use get_active_project'), but the context is strong enough to route correctly.

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