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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower and the description clears it by adding traits annotations cannot express: cursor passthrough semantics ('Follow next_cursor unchanged as after'), and job-state semantics ('Job success includes answer/references or output_id; partial remains explicit'). That tells the agent how to interpret a non-final result, which is genuinely useful behavioral context.

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?

The what-it-reads enumeration is front-loaded, and every subsequent clause (ID mapping, cursor rule, job-state note) carries distinct information. The phrasing is telegraphic to the point of awkwardness in places ('Follow next_cursor unchanged as after'), and the trailing editing hint is slightly orphaned, but nothing is padding.

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?

With 7 parameters, an output schema present, and strong annotations, the description covers the pieces an agent cannot infer: the view-to-ID mapping, pagination continuation, and partial-job interpretation. Return-value shape is legitimately delegated to the output schema. The missing `limit` explanation is the one substantive hole for a paginated listing tool.

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 14%, so the description must carry the burden — and it largely does: it defines which identifier each `view` requires and how `after` relates to the returned cursor. The gap is `limit`, which is never mentioned in the description and has no schema description either; an agent must infer its pagination role from the name alone. Against the low coverage baseline, this is above adequate but not exhaustive.

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 first sentence names a specific verb (Read) and enumerates the exact resource set: Hub sessions, one session, sources, chat history, a durable job, Studio outputs. That maps one-to-one onto the `view` enum, so an agent can tell this is the read-side counterpart to the create/delete/edit siblings. It stops short of naming any sibling explicitly, which keeps it out of 5 territory.

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?

It gives conditional routing within the tool (session_id for most views, job_id for job, output_id for output), which is real usage guidance, plus a workflow hint: 'Read the existing output before editing it.' But it never addresses when to use this versus adjacent readers like get_study, view_research_answer, or download_research_output, and never states exclusions or prerequisites beyond the ID mapping.

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