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

Annotations already declare this is a non-readonly, non-idempotent, non-destructive, closed-world write; the description goes far beyond by naming the exact 403 error codes (worker_not_key_owner, on_behalf_requires_owner_key), the permission tiers required, and the fact that actor and worker are both recorded on completion. None of this repeats the structured data and it is exactly the behavioral context needed to avoid a silent failure.

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 core action plus side effects are front-loaded, then the exclusion rule, then the key-tier rules – a sensible order. It is a single dense paragraph with heavy jargon, and a break between 'what it does' and 'authorization rules' would improve scanability, but every sentence carries information an agent needs.

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 write tool with annotations, full schema coverage, and no output schema, the definition covers side effects, authorization, and refusal modes well. It says nothing about re-completion of an already-completed task despite idempotentHint=false, and gives no hint of the returned handle, which is a minor remaining gap.

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, but the description adds real meaning about the two most ambiguous parameters: worker_id must be omitted or be the key's own worker for an agent key, while on_behalf_of requires an owner/admin-tier root key and is recorded separately. That interpretation is not derivable from the schema alone, so a 4 is warranted.

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 ('Complete an ORDINARY task'), plus concrete side effects ('Inserts a completion record and timer event'). It sharply separates itself from coordination-cycle work (CODE:/REVIEW: builds, decisions, questions, integrations, parked cards), which is the main confusion axis. It never distinguishes itself from the close sibling tascan_complete_subtask, so a small gap remains.

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 names the excluded case ('Coordination-cycle tasks ... are refused with 403') and says who handles them instead ('builds and reviews are completed by their runner, decisions only by the human on the worker page'). It also spells out which key tiers may call it, giving the agent a clear when/when-not decision rule with named alternatives.

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