list_sessions

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

With no annotations, the description carries the burden and does well: it discloses the trace-completeness filter, the pagination quirk ('a page can hold fewer and still have a next'), and how session_id relates to what a scoring run consumes. It does not cover authorization, rate limits, or errors beyond 'or an error message', so it stops short of a 5.

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?

Front-loaded with purpose and the Session definition, then ordered cleanly into alternative-tool guidance, parameter docs, and return note. It is long but nearly every line carries information; the trailing object-store boilerplate is generic filler that dilutes an otherwise tight definition.

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 list tool with no annotations and no output schema, the definition covers purpose, scope filter, all parameters, pagination, return shape, and how to handle the stored result object. Nothing an agent needs to call this correctly appears to be 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 description coverage is 0%, so the description must carry all parameter meaning, and it does: every one of the 8 parameters gets a semantic gloss, including the important 'every turn' semantics for origin/deployment_id/pipeline_version_id, ISO-8601 for since/until, the 200 cap for limit, and cursor being the previous page's 'next'. The only nit is that origin values are reworded rather than matching the enum literals.

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 ('Lists a pipeline's Sessions that a scoring run can judge') plus ordering ('newest last activity first'), and defines what a Session actually is (turns sharing a search_session_id, otherwise a single-turn query_id). It explicitly distinguishes itself from the nearest sibling by naming list_pipeline_traces and the use case that selects it.

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?

Gives explicit routing: use this for Sessions a scoring run can judge; use list_pipeline_traces with an OData filter when looking for Sessions that went wrong, and it even explains how to recover the session key from that path. The filtering constraint ('only Sessions whose every turn still has its trace') tells the agent when this tool will silently return less than expected.

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