update_task_details

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

The annotations already declare destructiveHint=false, so the agent knows this is non-destructive. The description adds behavioral context beyond annotations by specifying the ownership constraint ('Only tasks you hold, or tasks nobody has claimed, can be edited'), which is critical for safe invocation. However, it could also mention what happens on failure (e.g., if the task is claimed by another worker), earning a 4 rather than 5.

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 two sentences with zero wasted words. The first sentence is front-loaded with the verb and objects, and the second sentence adds critical usage constraints. Every sentence earns its place.

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?

Given the tool's moderate complexity (7 parameters, 1 required), full schema description coverage, presence of an output schema, and clear annotations, the description is complete. It covers purpose, usage constraints, and ownership rules without needing to explain return values (handled by output schema). No gaps remain for an agent to safely invoke this tool.

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 100%, so each parameter already has a description in the schema. The tool description adds value by grouping the parameters ('title, description, deadline or labels') and framing their purpose ('Refine a task's...'), but does not add new semantics beyond what the schema provides. A 4 is appropriate for good grouping without extra detail.

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?

The description uses a specific verb 'Refine' and clearly identifies the resources acted upon ('task's title, description, deadline or labels'). It also gives a concrete example use case ('after investigating and learning what the work actually involves'), which strongly distinguishes it from siblings like 'create_task', 'get_task', or 'move_task'.

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 explicitly states when to use this tool ('after investigating and learning what the work actually involves') and provides clear exclusion criteria: 'Only tasks you hold, or tasks nobody has claimed, can be edited; another worker's task is never touched.' This directly guides the agent on when not to use it and implicitly distinguishes it from related tools like 'claim_task', 'release_task', or 'update_status'.

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