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

Beyond the destructiveHint annotation, the description discloses the key behavioral nuance: the fact is kept and marked retired rather than deleted, it leaves the agent's context, and it remains visible to the athlete. The lapsed-fact distinction adds important behavioral context that annotations alone do not provide, and nothing contradicts the annotations.

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?

The description is compact and front-loaded with the core condition, but the phrase 'Always a card' is unexplained domain jargon that may confuse an agent. Overall, every sentence contributes meaning, though the conceptual framing is denser than strictly necessary.

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 two-parameter state-change tool with no output schema, the description explains the lasting effect, athlete visibility, and the lapsed exception. It does not describe the expected response or error handling, but those are partially covered by annotations and the simplicity of the call.

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 50%, so reason has a description but id does not. The description reinforces what a valid reason means by defining 'no longer true, or never was' and contrasting it with lapsed, but it adds no direct guidance on how to format or obtain id. This is adequate for a simple two-parameter tool, but not rich.

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 clearly identifies the operation as retiring a fact: removing an athlete's statement from the active context while marking it as no longer believed. It distinguishes this from deletion and from lapsed facts, so an agent can differentiate retire_fact from update_fact and confirm_fact without opening schemas.

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 gives explicit when-to-use conditions: retire a fact when it is no longer true or never was. It also gives an explicit when-not-to-use condition: a LAPSED fact is not automatically retired, and the agent should ask first. This is clear usage guidance even without naming sibling tools.

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