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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety and repeat-safety profile is fully covered without the description. The description adds only the legitimately useful note that legacy tests are supported, but says nothing about pagination, result caps, or performance on large sessions. Modest added value against an already-complete annotation set.

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?

Four tight sentences; the core purpose leads, then routing, then parameter notes. Nothing is redundant with the schema or annotations, and the trailing legacy-tests note is short.

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?

An output schema exists, so return values need no explanation, and the safety profile comes from annotations. However testId (required) and runId are never characterized in description or schema, leaving an agent to guess their relationship and whether runId narrows results. Adequate but with a real gap.

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 low (25%), so the description must compensate. It does add real meaning for testerName (optional, case-insensitive partial-name filter; omit for all testers) and reiterates blockId's omission default, but testId and runId carry no semantics anywhere. Partial compensation only.

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 (List) and resource (AI-tester session transcripts), and adds scope detail: exact refs plus step counts for clicks, reasoning and screen-by-screen behavior. It implicitly distinguishes from list_human_sessions by specifying AI-tester sessions, though it doesn't explicitly name that sibling. Clear and specific overall.

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 a real routing rule: post-test answers go to list_test_questions and get_test_question_responses instead. It also points to list_test_blocks as the source of block/run IDs and explains the omission default. It never clarifies this tool versus get_transcript, which is the closest-looking sibling.

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