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

Annotations only declare destructiveHint/idempotentHint/readOnlyHint; the description goes well beyond them by spelling out derived side effects (status='in_progress' auto-fills start_date, terminal status auto-fills completed_at, reopening clears completed_at unless overridden) and warning that tags is a full replacement of the existing list. That is exactly the 'what gets destroyed / what changes as a side effect' context the annotations cannot 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?

Front-loaded with purpose, then mutation semantics, then parameters — the most decision-relevant information (partial update, side effects, tag replacement) comes before the arg list. The Args block is long but each line adds semantics not present in the bare schema.

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 10-param mutation tool with no output schema, the description covers purpose, partial-update semantics, side effects, and all parameters. Gaps are minor: it says nothing about behavior when task_id is unknown/invalid, nor what the call returns or whether permission is required.

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?

With 0% schema description coverage across 10 parameters, the description carries the full burden and does so: it documents every param, gives the status enum values, and crucially explains the priority 0.0-1.0 range with the sentinel 'negative = unchanged' (schema default -1) plus the backfilling intent of created_at/completed_at. This is meaning a caller could not recover from the schema alone.

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 ('Update fields of a standalone task') and the scope is narrowed with 'standalone', which distinguishes it from agent task tools like complete_agent_task. However it never names the near-siblings complete_task/delete_task, leaving the agent to infer the boundary between a status update and dedicated lifecycle tools.

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?

'Only the fields you pass change' implies partial-update usage, which is genuinely useful context. But there is no explicit guidance on when to choose this over complete_task (which presumably sets a terminal status) or update_goal, and no stated prerequisites or exclusions. Usage is implied rather than directed.

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