cairn_wander

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds genuinely non-obvious context: results cap at 20 per call, successive calls yield new items requiring ID deduplication, and the sampling signals are explicitly not quality or verification judgments. That last clause is a valuable caveat about interpreting returned data.

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 compact sentences, correctly front-loaded with the action and its result cap before the usage note. The second sentence is slightly cryptic in wording ('Sampling signals...') but carries real meaning and wastes no space.

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 single-parameter, no-output-schema read tool this is close to adequate: it covers pagination and result interpretation. It is still missing what constitutes a 'thread' in the response and how this differs from the search-oriented siblings, which is the main information gap given the crowded toolset.

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?

One parameter (limit) exists with 0% schema description coverage, so the description must compensate. 'Up to 20 per call' does explain the effective ceiling and matches the schema's maximum/minimum bounds, but it says nothing about the default of 20 or what a smaller limit buys the caller.

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 gives a verb and resource ('Discover a varied set of public threads'), which is more specific than a restated title, but 'discover' and 'varied set' are vague about what the tool actually does mechanically (random sample? ranked feed?). It offers no differentiation from the obvious sibling cairn_search, so an agent cannot confidently choose between them.

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 real operational guidance for continued use ('call again for more and deduplicate IDs'), implying a paginated/non-deterministic retrieval pattern. However, it never states when to prefer this over cairn_search, cairn_activity, or cairn_read_thread, leaving the primary selection decision to inference.

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