history

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

Annotations only declare read-only/idempotent/non-destructive. The description carries the behavioral load: revisions are retired not deleted, a stale kb-id still resolves to the replacing text, and the enumeration has an edge case (revised once = two revisions; never revised = one). These are non-obvious behaviors an agent could not infer from annotations or schema.

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?

Three sentences, each earning its place: the core behavior, the exact condition to invoke under, and the count edge cases. The key trigger is mid-placed.io keeping the description under ~50 words with zero 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?

With no output schema, the description acts as the return contrat; enumerates all revisions oldest first and names the current one. For a single-parameter, no-nested, no-enum tool it covers case, trigger, and edge cases — by not of what an agent needs to invoke it correctly.

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Schema coverage is 100% ('Any revision, current or superseded'), so the baseline is 3. The description adds value by explaining what 'superseded' means operationally — that a stale/id no longer in search still resolves to its replacement — which is material to acceptable values beyond the schema's one-line description.

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 the exact operation — 'List every revision of a section' — plus the ordering (oldest first) and the distinguishing output behavior (names the current one). This is specific verb+resource language and clearly separates it from siblings like content, retrieve, recall, and revise, none of which claim revision enumeration.

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 an explicit trigger: 'Call it when a kb-id you hold no longer appears in search.' It also explains the rationale (revisions are retired, not deleted) so an agent can recognize the staleness scenario and route here instead of re-running search or retreating. This is direct when-to-use guidance with a named alternative behavior.

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