Edit a task

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

Annotations already declare the safety profile (readOnly=false, destructive=false, idempotent=true, openWorld=true), so the bar is lower. The description usefully adds an authorization requirement and, importantly, the meaning of null (clears description, acceptance criteria and dates) plus the one-shot limit on estimate entry. It does not cover return behavior, error cases, or what happens to fields not sent beyond the general 'send only what changes' rule.

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?

Two short sentences, zero filler, with the core mutation semantics up front and the null-clearing rule immediately after. Nothing is repeated from the schema or annotations.

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 9-parameter mutation tool with no output schema, the definition covers identity, permission, partial-update and null-clearing semantics, which is most of what an agent needs to call it safely. The remaining gap is that per-field editable semantics and the surprising 'Default: now' on the timestamp fields are not reconciled with the update behavior.

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 only 11% across 9 parameters, so the description has to carry meaning, and it does explain the null sentinel for description, acceptance_criteria and dates, which the schema's anyOf[null] does not. But it never explains task (number vs id), title, category, priority, estimate_minutes or the two timestamp fields, and the schema's 'Default: now' note on due_at/planned_start_at is left unaddressed for an update operation.

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 ('Changes a task's details') and distinguishes a second mode ('gives your estimate as its assignee (once)'), which no sibling name alone would convey. It stops short of naming siblings like assign_task or complete_task, so the boundary with those is left to inference.

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 concrete context for use: the caller needs 'Edit tasks' permission, and the estimate path is limited to being the assignee and only works 'once'. It also states partial-update semantics ('Send only what changes'), but offers no explicit when-not guidance or named alternatives for the assign/move/complete family.

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