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

Goes well beyond the annotations: it discloses that only drafts are touched, that the data reaches nobody, the two failure modes and their codes, the required permission ('timesheets:write' / 'Submit your timesheets'), the acting-on-behalf-of model, and the sign-in prompt if the member hasn't connected. It also carries a prompt-injection caution about member-written text.

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?

Purpose is front-loaded and every sentence adds operational information — scope, error codes, permissions, auth, injection warning. The trailing injection sentence is boilerplate policy rather than tool-specific, which costs a small amount of focus but is not wasted in a security sense.

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 destructive single-parameter tool with no output schema, the description covers everything an agent needs: what gets destroyed, what happens on invalid targets, what authorization is required, and what the sign-in interruption means. Annotations and description reinforce rather than duplicate each other.

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?

Only one parameter exists and the schema already describes it at 100% coverage ('The timesheet id.'). The description adds the useful framing that the id belongs to the member's draft week, but no format, range, or lookup guidance beyond what the structured field provides.

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 ('Discard') and resource ('draft timesheet'), then narrows the scope to 'DRAFT weeks (never sent, so it reaches nobody)'. This clearly separates it from update_timesheet_draft, submit_timesheet, and delete_work_draft without requiring the schema to be opened.

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 explicit when-not-to-use conditions, naming the exact 409 codes (ALREADY_SUBMITTED, TIMESHEET_WAS_SENT) that mark a week as out of scope, and points the member to the site to withdraw those. It stops short of naming sibling MCP tools as alternatives, which keeps it from a 5.

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