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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description goes further by disclosing the two-phase lifecycle — a PENDING suggestion is written and the due date is only applied on human accept. That is genuinely useful behavioral context. It doesn't say what happens on rejection or whether the reviewer is notified.

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, front-loaded with what the tool does, then behavior, then when to use it. Every sentence carries distinct information and the trailing date-format note is the only mildly redundant element.

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?

With no output schema, the description still conveys the key outcome (pending suggestion, applied on accept), and annotations cover the safety hints; parameters are fully documented in the schema. What's absent are the post-rejection path, reviewer notification behavior, and whether the proposal can be withdrawn — minor gaps for an approval-workflow tool.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 all three parameters (taskId, newDueDate, reason) are already documented in the schema, including the YYYY-MM-DD format the description repeats. The one added nuance is that the change is 'typically' an extension, implying newDueDate may move either direction — modest value over an already complete schema, so baseline 3.

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 gives a specific verb and resource ('Propose changing a task due date ... for human review') and clarifies the scope is a PENDING suggestion rather than a direct edit. It does not explicitly name the close siblings (propose_status_change, propose_task_split, propose_assignment), but the resource noun makes the tool distinguishable without opening a schema.

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?

It states the triggering condition clearly ('when a task is blocked or slipping') and contrasts with the alternative of silently moving the date, which implicitly routes the agent to update_task. It stops short of naming that alternative tool or stating exclusions (e.g. don't use if you have authority to move the date directly).

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