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

Annotations already declare readOnly/idempotent/non-destructive, so the redundant 'Read-only' adds little. However, the description goes well beyond structured data by decoding domain semantics: what held_by_breaker means, how autopilot_status/running_for relate, and what paused_reason governs.

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?

Front-loaded with the core purpose and free of filler, but it is one very long run-on sentence whose parenthetical asides make it dense. Every clause carries field meaning, so size is justified even if readability suffers.

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 carries the burden of explaining returns and does so for the major fields (status, cap, waiting-on, queue, recent activity), giving an agent enough to interpret results. Minor return fields likely remain unexplained.

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?

Single optional parameter with 100% schema description coverage, so the schema already documents app_id and its 'omit for the running project' default. The description's 'default: the project it runs for' merely echoes the schema, adding no syntax or format 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?

States a specific verb+resource (get the Discovery Autopilot state for a project) and enumerates what 'state' comprises (status, cap usage, waiting-on, approval queue, recent activity). It is clearly a getter contrasted with the set_autopilot sibling, though it never explicitly names that contrast.

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?

Usage is implied rather than stated. The clause about the default project and the note that set_autopilot clears held_by_breaker give context, but there is no explicit 'use this when...' guidance or named alternative for retrieving different state.

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