run_saved_filter

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

With no annotations, the description carries the full burden. It discloses pagination, that results are returned, and that sorting is pre-configured in the UI. However, it does not mention error behavior (e.g., filter not found) or whether the operation is read-only (though implied). The description is helpful but could be more comprehensive.

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 description is efficient: two sentences that cover purpose, key differentiators, and usage hint. No redundant words. Front-loaded with the main action.

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?

Given the lack of an output schema, the description could be more explicit about the return structure (e.g., fields returned, pagination metadata). It says 'return its results, paginated' which is adequate but not fully complete. However, the strong parameter and usage guidance compensate partially.

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?

The input schema covers 60% of parameters with descriptions. The description adds context for the 'entity' parameter (kases for projects) and clarifies that 'id' comes from list_saved_filters. It does not add much for pagination parameters beyond schema defaults, but overall complements the schema well.

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 explicitly states it runs a saved filter by id and returns paginated results. It differentiates from sibling tools like filter_parties by highlighting that saved filters support sort while ad-hoc filters do not. The verb 'run' and resource 'saved filter' are specific and clear.

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 description provides explicit guidance: use list_saved_filters first to find an appropriate saved filter, and contrasts with ad-hoc filter tools for when sort is needed. It also implies when to use this tool (when a saved filter exists with configured sort) versus when not (if no suitable saved filter exists).

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