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

Goes well beyond annotations: explains that minutes are incremental, that negatives correct over-counts, that values outside -100000..100000 are refused, and that the counter is scoped to the board. This is critical behavioral context the annotations do not 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?

Three sentences, each earning its place: purpose, add/correct semantics, and bounds/scope. No filler or redundancy. Front-loaded with the core action.

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?

Complete for a simple two-parameter mutation tool: it covers purpose, mechanics, bounds, and scope. It doesn't describe the success response, but no output schema exists and the additive behavior makes the outcome self-evident. Minor gap: no mention of prereq such as task existence, but that's implied by 'task id'.

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 schema already describes 'Minutes to add; a negative number corrects an over-count'. The description adds the real-worked context and board scope but does not materially extend parameter meaning beyond the schema.

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: 'Add real minutes worked to one task'. It explains the purpose (estimate vs actual comparison) and clarifies the additive semantics, which distinguishes it from other task mutation tools like task_start_timer or task_update.

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?

The description implies when to use it (to log actual time worked against a task) but never explicitly names alternatives or says when not to use. Sibling tools like task_start_timer and task_update exist, but the description doesn't guide selection between them beyond purpose.

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