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

Annotations only say readOnly; the description adds the crucial behavior that the call can return analysisStatus 'analyzing' and ready: false while the site is being read, and that the agent should retry after a delay. It also discloses a global output rule (posts are always sentence case regardless of the brand's website) that is not in structured fields.

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-loads the return contents, then the alternative, then the async-status caveat — sensible ordering. The sentence-case statement is tangential to what the tool returns, though it does convey a brand-writing rule an agent may need later.

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 simple one-parameter read with no output schema, the description covers both the normal return shape and the pending-analysis case, which is the main failure mode an agent would hit. Nothing important appears to be 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?

Schema coverage is 100% and the only parameter, projectId, is already described in the schema (with its source, list_projects). The description adds no parameter-level syntax or formatting details, so the baseline 3 applies.

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 ('Returns the project's brand profile') and enumerates the contents: voice, audience, products, colors, typography. This clearly distinguishes it from sibling update_brand, which writes the same profile.

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?

Gives the read/write split against update_brand and, more usefully, states exactly when to call it again (after create_project or reread_website) and what to do (wait a minute). It does not say when NOT to call it, but the practical guidance is strong.

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