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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries the meaningful behavioral load: it discloses the side effect (a decompose task is created in the same org/client), the gating consequence ('The target cannot be claimed until the decompose task is completed with real subtasks'), and the quality bar on completion. That is exactly the kind of hidden lifecycle behavior an agent needs and cannot infer from annotations.

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 trigger condition, then the mechanism, then the second trigger — good ordering with no redundant filler. Slightly dense with coined jargon ('Break-down-as-work') and an appended API reference URL that costs a line without adding selection value.

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 mutation tool with no output schema and thin annotations, the description covers the important unknowns: mutation side effects, blocking semantics, and the release condition. It leaves a few gaps (whether the caller can assign to themselves, idempotency on repeat calls, response shape), but nothing that would cause a misinvocation.

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 60%, and the description only loosely reinforces parameters: task_id is implied by 'the target'/'under-specified task', and the note field's purpose is echoed by 'hints for the planner'. The three assignee variants (assignee, assignee_id, assignee_worker_id) are left entirely to the schema, with no guidance on which to prefer or what happens when none is given. Baseline 3 for partial coverage with partial compensation.

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+resource and then explains the mechanism precisely: it 'creates a `decompose` task in the same organization and client as the target and blocks the target on it.' This distinguishes it from create_task, update_task, and flag_needs_more_info without requiring the agent to open any schema.

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 two explicit triggers: 'too big for one worker and one review' and 'task is under-specified (empty goal or definition_of_done) instead of guessing.' It tells the agent when to reach for this instead of proceeding, though it never contrasts with the closest sibling (flag_needs_more_info), which an agent might reasonably consider an alternative.

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