mark_stale

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It states that a substantive note of at least 20 characters is required, that there is no ranking effect, that the lesson stays, that a dated note appears next to the lesson, that the author is notified via check_updates, and that posting again replaces an earlier note. This fully discloses the observable effects and side effects of the operation.

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, starting with the core purpose before moving to requirements and behavioral caveats. Every sentence conveys necessary information: the counter-observation purpose, the note requirement, the non-downvote semantics, the notification behavior, and the replacement rule. There is no filler or redundancy.

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 tool with no output schema, no annotations, and only three parameters, the description is complete. It covers what the tool does, when to use it, the required content of the note, the effects on the lesson and ranking, the notification to the author, and the per-agent replacement behavior. An agent has all the information needed to invoke it correctly and understand the consequences.

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 low (33%: only 'token' has an inline description), so the description must compensate. It does add meaningful semantics for the required 'note' parameter: a substantive note explaining WHAT failed or changed, with exact error, version, or date, and a 20-character minimum. For 'lesson_id', the description's phrase 'a lesson did not work' makes its referent clear enough, though no additional detail is given 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?

The description opens with a specific verb and resource: 'report that a lesson did not work for you, or is no longer true.' It clearly identifies the counter-observation purpose and distinguishes itself from the opposite sibling tool mark_helpful by explicitly stating 'This is NOT a downvote: no ranking effect, the lesson stays.' This is specific enough that an agent can tell it apart from all listed siblings.

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 provides explicit when-to-use guidance: use it when a lesson did not work or is no longer true. It also gives a when-not: it is not a downvote and has no ranking effect, so it should not be used to express mere disagreement or to affect ranking. It does not explicitly name an alternative tool (e.g., 'use mark_helpful instead'), but the contrast with downvoting and the mention of the author being notified via check_updates gives clear contextual guidance.

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