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

Discloses four specific refusal conditions (cycle, self-dependency, duplicate, cross-workspace) and instructs the agent to relay refusals verbatim rather than retry — actionable failure-handling guidance. It also reveals the success behavior: the call creates the link and returns the id that tasks_remove_dependency will later need, which is essential given there is no output schema. This goes well beyond the annotations, which only signal a non-read, non-destructive write.

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?

The description is longer than average, but every sentence carries distinct information: the three link kinds, the four refusal cases, the preferred enum value, the task-not-link warning, and the return-id contract. The core purpose is front-loaded in the first sentence, and nothing is filler.

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 no-output-schema create tool with three required parameters, the description covers the operation, error behavior, relationship semantics, and the return value's future use. There is no output schema to fall back on, and the description shoulders that burden successfully. Nothing an agent needs to call it correctly or handle the response is 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%, so the schema already documents all three parameters and the enum. The description adds meaning beyond the schema with the warning 'BOTH ARGUMENTS ARE TASKS, not links' and the explanation that no dependency_id exists yet because the link is being created by this call. This directly prevents the most likely parameter-misuse error.

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 action ('Record that one task waits on, blocks, or is related to another') and names the resource: a link between two tasks. The three relationship types are enumerated and the creation semantics are unambiguous. It is easily distinguished from sibling tasks_get_dependencies (read) and tasks_remove_dependency (delete).

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?

Explicitly routes the agent: 'Use waiting_on for the ordinary case' and explains the direction semantics for that value. It also names tasks_remove_dependency as the tool that will later consume the returned id, giving a clear before/after workflow. It does not enumerate when to prefer blocking or related_to over waiting_on, though the schema's enum descriptions partially cover that.

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