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

Annotations only say this is a non-destructive, non-open-world write; the description adds the things annotations cannot: a seat prerequisite with a named failure mode ('if it refuses with SEAT_NOT_BOUND, register and try again'), a duplicate-logging warning, and an integrity rule against unsubstantiated cost_cents. That is exactly the context an agent needs before invoking a write tool.

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 core action and its effect, and nearly every sentence carries an operational constraint. There is mild redundancy between 'One call per completed piece of work' and 'Do not log the same work twice', which could be merged without losing 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?

For a 3-parameter write tool with no output schema, the description covers the prerequisite, the failure-and-retry path, idempotency, and data-integrity expectations — everything an agent needs to call it correctly without trial and error.

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; the description earns above that by constraining summary to 'one or two sentences' and by adding a substantiation rule for cost_cents that goes beyond the schema's 'never estimate upward'. The optional category parameter is not addressed in the description at all.

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 ('Report a piece of work you have COMPLETED') plus the observable effect ('shows on your chart tile and in the organization's activity'), which tells an agent what it produces, not just what it does. The temporal qualifier ('after it is done') separates it from planning-oriented siblings like add_todo or create_schedule.

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 an explicit when ('one call per completed piece of work, after it is done') and an explicit when-not ('never for work you only planned or started'), which is unusually clear. The gap is that it never routes against the closest sibling, complete_todo, so an agent that just finished a tracked todo still has to guess whether to log_work, complete_todo, or both.

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