skylight_list_chores

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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=true), and the description goes beyond them by disclosing the response contract: assignee lives in `category_id`, completer in `completed_category_id`, and the singular/plural key switch that signals multi-assignment vs unassigned. That absent-singular-means-unassigned rule is genuinely non-obvious and prevents a real misread; pagination and result limits are not addressed, keeping it at 4.

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 first sentence front-loads purpose and the two scoping facts; the remaining sentences are dense but each carries a real disambiguation rule about response keys. There is no filler, though roughly three-quarters of the text serves return-value semantics rather than invocation, so the emphasis is slightly skewed.

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 is right to explain return fields and does so well, and it names skylight_list_categories for name resolution. It is still incomplete on two call-relevant points: whether `frameId` is optional or how to source it (skylight_list_frames is never referenced), and any notion of result size or ordering.

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 67%: `after` and `before` are already documented in-schema with YYYY-MM-DD format and inclusivity, so the description's 'required date range' adds little. `frameId` is undocumented in both places, and the description only alludes to it via 'for a Skylight frame', never explaining how to obtain or default it. Baseline 3 fits.

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?

States a specific verb and resource ('List chores') plus its scoping constraint ('within a required date range'), which is enough to distinguish it from mutation siblings like skylight_update_chore or skylight_complete_chore. It does not, however, differentiate itself from skylight_search_chores, the most likely alternate read path.

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 'required date range' wording implies the caller must supply bounds, and it points to skylight_list_categories for resolving assignee names — a useful cross-reference. But it never says when to use this instead of skylight_search_chores or skylight_list_tasks, so the when-to-use decision is left to inference.

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