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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds genuinely new behavior: a hard page size of 20 and cursor-based resumption. It stops short of explaining ordering, total counts, or termination conditions, and the cursor is called 'next_after' while the schema parameter is 'after'.

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 terse fragments ('at most20' missing a space) that are under-specified rather than efficient. Front-loading is fine, but the compression drops the verb and the object's definition, so the size is a defect rather than a virtue.

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 and no parameter descriptions, the description carries the full burden of the pagination contract. It omits what a 'fire' is, how results are ordered, what the response looks like, and how an agent knows the last page has been reached.

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?

Only one parameter ('after', 0% schema coverage), and the description does gesture at its meaning as a resume cursor. But it names it 'next_after' rather than 'after', leaving the agent to guess the mapping between the returned cursor and the accepted argument.

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 conveys that this returns one paginated page of 'fires' (max 20), which roughly matches the name yac_list_fires and distinguishes it from the singular yac_read_fire. However, it never states the verb explicitly ('list') and 'public V1 directory page' and 'fires' are undefined jargon an agent cannot resolve.

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?

'resume next_after' hints at the pagination loop, but there is no statement of when to use this tool versus yac_read_fire or yac_changes, and no prerequisites or exclusions are given. The agent must infer routing entirely from the tool name.

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