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

Annotations already establish a safe read (readOnlyHint=true, openWorldHint=false), and the description adds genuinely new facts: credentials are never returned, the status can be ready / failing-with-reason-in-last_check / unchecked, and the exact error code on an unconfigured project. That is meaningful behavioral context beyond the structured hints.

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?

Three tight sentences, front-loaded with the resource and its returned fields, then the visibility constraint, then the failure mode. No filler or 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?

With no output schema, the description correctly enumerates what is returned and what is withheld, plus the error case, which is sufficient for a one-parameter read. The only real gap is the unresolved overlap with check_sender for an agent choosing between them.

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 description coverage is 0% for the single project_id parameter, so the description has to carry the meaning. 'The project's sender' implies the parameter scopes to a project, but it never states whether project_id is an ID or a slug, or where to obtain it.

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?

Specific verb+resource ('Read the project's sender') immediately followed by the exact fields returned: provider account email, from address, hourly cap, and readiness status. An agent knows exactly what comes back. It does not, however, differentiate itself from the sibling check_sender, which sounds like it may read the same resource.

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?

Usage is only implied by the phrasing 'Read the project's sender' — there is no explicit statement of when to call this versus check_sender, get_sending_domain, or update_sender. The 'Fails with sender_not_found when none is connected' line gives a useful precondition signal but is not a when-to-use rule.

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