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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description earns credit for the context it adds: authorization is re-checked on every read, audio eligibility requires a complete participant turn and an owned recording, and evidence carries canonical transcript locators. These are real constraints an agent would otherwise have to discover by failure.

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?

Three dense sentences with the primary capability front-loaded and the operational caveats (pagination, authorization) following. No filler, though the compressed noun list requires re-reading and the `next_cursor` naming drift costs a little clarity.

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 not be described, and annotations carry the safety profile. Combined with the description's disclosure of auth re-checks and audio-eligibility rules, an agent has enough to call this correctly, even if the exact view-to-content mapping needs a schema peek.

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 only 17% (only `organization_id` is documented), so the description must carry most of the burden. It partially compensates by enumerating the readable content types that correspond to `view` values, but never names the enum values, never explains `run_id` vs `session_id` vs `evidence_id` selection, and refers to a `next_cursor` field while the request parameter is actually called `after` — a terminology mismatch that could send an agent looking for a nonexistent argument.

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?

Opens with a specific verb ('Read') and enumerates the resources available: run, verified claims, evidence, timed highlights, exports, source coverage, session history. This maps well onto most of the `view` enum. It does not differentiate itself from overlapping siblings such as `inspect_research_session`, `view_research_answer`, or `get_research_deliverable`, so an agent cannot resolve those collisions from the description alone.

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?

Usage is implied: the enumerated content types tell the agent this is the inspection surface for analysis output, and 'Follow next_cursor until exhausted' gives a concrete iteration instruction. There is no explicit when-to-use / when-not-to-use guidance and no naming of the sibling that handles raw session data or file downloads instead.

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