get_recovery

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context: that the original idempotency key must be reused and that a missing receipt does not authorize a new key. This is meaningful behavioral disclosure beyond annotations, though it is phrased cryptically and says nothing about return contents.

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 sentences, both dense and front-loaded, with no filler. The second sentence is syntactically convoluted but still earns its place as a behavioral warning.

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, so return values need not be explained, but the tool involves non-trivial idempotency/recovery semantics and three undocumented parameters against 0% schema coverage. The description covers the key idempotency rule but omits what campaign_id and branch_id scope, leaving it only minimally adequate.

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 0%, so the description must carry parameter meaning, but it only obliquely references the idempotency_key as 'original key'. campaign_id and branch_id are entirely undocumented in both schema and description. The description partially compensates for the coverage gap but leaves most parameters unexplained.

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 action on specific resources ('read every pending check', 'look up an exact committed receipt'), giving a verb+resource pairing. However, terms like 'pending check' and 'committed receipt' are undefined domain jargon, and it never distinguishes this tool from siblings like roll_check or restore_checkpoint. It conveys intent but leaves the exact purpose partially opaque.

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 second sentence ('No receipt at read time is not permission to replay with a new key') is a behavioral caution, not guidance on when to choose this tool over alternatives. There is no statement of when to invoke it versus restore_checkpoint, roll_check, or get_state. Usage must be inferred.

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