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

Adds substantial context beyond the destructive annotation: the held turn-down behavior, the confirmation_token round-trip, and the note that nobody is hired or rejected by score. It does not mention reversibility or that undo_change is available, leaving a minor gap for a destructive mutation.

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-loads the verb and resource, then walks the parameters in a compact list before closing with the held-confirmation rule and the `say` summary. Every sentence carries information, though the parameter block is dense.

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 5-param destructive mutation with no output schema, it explains each setting, the held-confirmation protocol, and points to the `say` summary field. Only the post-success behavior and recovery path (undo_change) are unstated.

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 only 20% (confirmation_token), but the description documents all five parameters with real semantics, including valid ranges (50-97 for shortlist_at_match, 7-60 for turn_down_after_days) and the relationship between turn_down_after_days and turn_down_note. This compensates far beyond the schema.

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 ('Change') and resource ('the employer's own Screening Autopilot'), which clearly separates it from read siblings like get_screening_autopilot and autopilot_status. It does not explicitly differentiate from nearby write siblings switch_autopilot or autopilot_settings, so it falls just short of a 5.

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 phrase 'at their request' implies user-initiated use, and the confirmation-token flow implies a two-step interaction, but there is no explicit when-to-use guidance or comparison to alternative tools like switch_autopilot or autopilot_settings. Usage is implied rather than stated.

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