Task Recovery Plan

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

The annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this by explicitly stating it is read-only and never replays work. It adds the side-effect-aware nature of the plan without contradiction. It could disclose the return shape or plan structure, but annotations cover the safety profile well.

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 crisp sentences with zero waste. States purpose, triggers, and a safety qualifier. Front-loaded with the primary action first.

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 it has an output schema (so return values are documented elsewhere), read-only annotations, and 75% parameter coverage, the description provides sufficient context. It could note what consequences or plan contents are most important, but the output schema presumably handles that. Solid completeness for a read tool with good structured metadata.

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 75%, and three of four parameters have descriptive schema text covering workspace binding, conversation id, and generation semantics. The description adds the 'side-effect-aware' context but doesn't add meaning beyond the schema for the parameters. Baseline 3 applies given the high schema coverage.

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 states a specific verb+resource (Read a unified, side-effect-aware recovery plan) with clear scope: before resuming a Goal, Durable Job, or Handoff. It differentiates itself from read/write siblings by explicitly noting it is read-only and never replays work, distinguishing it from task_status and run_task_status.

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 gives clear context on when to use (before resuming a Goal, Durable Job, or Handoff) and includes an implicit exclusion by explicitly declaring it never replays work. It doesn't name alternative tools for the 'when-not' case, which is the only gap.

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