task_edit

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

Annotations only declare readOnlyHint=false, so the description adds real value: planner-only authorization, draft/planned-only scope, empty string as a clear operation, and a redirect for started tasks. It does not say what happens if a started task is passed (error vs silent no-op) or whether the edit is reversible.

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?

Three short sentences, each carrying a distinct constraint: what can change, who may call it, and where started tasks go instead. Nothing redundant.

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?

There is no output schema and no annotations beyond a mutation flag, so the description carries the burden of telling the agent what a successful edit returns and what failure looks like. It covers scope and preconditions but not outcomes or the meaning of the required 'by' credential.

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 0% and five parameters exist, so the description must compensate. It does well on 'spec' (path + section, empty clears) but leaves 'id' and especially 'by' unexplained, and it calls the parameter 'spec_source' while the schema names it 'spec', which can cause a mis-mapped argument.

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?

Specific verb plus a concrete list of editable fields (title, spec_source, verification_cmd) scoped to draft/planned tasks. It clearly separates itself from task_note, but does not explain how it differs from the very similarly named sibling task_update, which an agent would have to guess between.

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?

'Planners only' states the precondition, 'pass at least one of...' states the invocation constraint, and 'Started tasks take task_note instead' routes to an explicit alternative. It stops short of saying when to use it versus task_update, the sharpest ambiguity here.

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