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

With no annotations, the description does disclose that the operation is read-only and enumerates the returned state values, which is meaningful behavioral context. It does not cover permission requirements, error behavior, or what 'current action' contains.

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 short sentences front-load the read-only status and then state the returned information. There is no filler, and every phrase carries relevant meaning.

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 simple single-parameter read, the description gives the operation shape and return states, but it omits how to source search_id and does not disambiguate from sdr_run_states. With no annotations or output schema, that leaves a few operational gaps.

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?

There is one required parameter and schema description coverage is 0%; the phrase 'of a search' ties search_id to a search but does not explain where to obtain the ID or reinforce its UUID format. The schema itself supplies type and format, so this is minimum viable rather than fully compensatory.

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 states the resource (a search), the exact returned states (running / paused / idle), and that access is read-only. It is clear, but it does not distinguish this singular tool from the nearly identical sibling sdr_run_states or from sdr_get_search.

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?

There is no explicit guidance on when to choose this over sdr_run_states, sdr_get_search, or sdr_list_searches. The only implied condition is supplying a single search_id, so an agent must infer the use case.

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