list_sessions

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

With no annotations the description carries the full burden, and it delivers: it discloses a silent filtering rule (only Sessions where every turn still has its trace), pagination behavior (limit capped at 200, a page may hold fewer and still carry a next), and the side effect that output is auto-stored as an object ID for reuse. It stops short of stating read-only semantics or any auth/permission requirements, which is the only gap.

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?

Purpose and routing come first, then semantics, then parameters, then returns — well front-loaded. The parameter list and object-store paragraph are verbose, but the param block is justified at 0% schema coverage; the four-sentence object-store boilerplate is the one part that could be trimmed.

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 an 8-parameter, no-output-schema, no-annotation list tool, the description covers filtering semantics, the trace-completeness caveat, pagination/cursor mechanics, and how to consume the returned object ID. Nothing an agent needs to call it correctly is missing.

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 0% (titles only), so the description must compensate and does: every one of the 8 parameters is explained with meaning beyond the name, including the per-turn constraints on origin/deployment_id/pipeline_version_id, ISO-8601 formats for since/until, the 200 cap on limit, and that cursor is the previous page's next value. The origin wording maps onto the SERVICE/PIPELINE_RUN/PLAYGROUND enum.

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 (lists) and resource (a pipeline's Sessions) and then defines what a Session actually is (turns sharing a search_session_id, or a single-turn Session named by query_id). It also distinguishes itself from the sibling list_pipeline_traces by naming the filter-based alternative for finding bad sessions, so an agent can pick between them without opening either schema.

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?

Explicitly routes the agent: use this for Sessions an Experiment run can judge, but use list_pipeline_traces with an OData filter to find Sessions that went wrong (failed turn, negative feedback), and read search_session_id/query_id from those rows. The exclusion condition and the alternative are both named.

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