search_cards

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds two genuinely useful behavior notes — that unspecified searches default to title matching, and that pagination should continue via next_offset — but says nothing about result caps, cursor reuse across text_offsets/section_offsets, or the previous_page fingerprint check that the schema hints at.

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 short sentences, front-loaded with the core action and free of filler. The terseness comes at a small cost: phrases like 'documented filters' and 'Full detail requests descriptions' are compressed to the point of ambiguity.

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 43-parameter search tool with nested offset objects and a low-coverage schema, the description is far too thin. The output schema offsets the need to explain return values and the annotations cover safety, but the filter vocabulary, cursor mechanics and sibling routing are all left unexplained.

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 7% across 43 parameters, so the description would have to carry almost the entire burden — and it does not. It clarifies only a handful of concepts (default search field, detail=full returning descriptions, filter/sort/limit-offset trio), leaving the dozens of ref-based filter parameters (states, lane_id, tag_ids, due_date_*, *_moved_* timestamps) with no meaning added anywhere.

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+resource ('Search cards') and goes on to name the capabilities that matter: filters, sorting, limit/offset. It does not, however, differentiate itself from the list_space_cards / list_board_cards siblings, so an agent still has to guess which tool to reach for when a search could be scoped to a space or board.

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 only quasi-guidance is 'Defaults to title search' and 'Follow next_offset', which describe behavior rather than when to choose this tool over the many list_* siblings. There is no statement of prerequisites, no when-not-to-use, and no explicit alternative named.

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