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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds real operational context on top: paid, owner-only authorization, no live orders or model inference, keyless subscription gating with a subscribe path, and the key behavioral fact that the full study is surfaced in the Research App rather than returned wholesale here. That answers the agent's access-prerequisite and output-expectation questions better than the annotations alone.

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 the core action and kept to a few short clauses with no filler. The trailing 'Access: keyless: subscription_required with a subscribe link' is dense and telegraphic, but it is carrying genuine prerequisite information rather than 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?

For a one-parameter, non-destructive read with no output schema, the definition covers the important unknowns: who may call it, that it costs money, that it returns nothing live, and that the substantive report is rendered in the Research App. Only the exact shape of the returned payload is left implicit, which is a minor gap given the app-pointer statement.

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 100% and the run_id property already documents the 32-lowercase-hex format and the 'from an owned run result' provenance. The description only echoes the ownership constraint ('owner-only'), adding no format or sourcing detail beyond the schema, so the baseline 3 applies.

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: reading a single saved study, contrasted with the sibling research_run_list which enumerates runs and research_run_cancel which mutates. The scope is unambiguous for an agent, though it never explicitly names the sibling used to discover a run_id.

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 rather than stated: the reader learns it applies to an already-saved, owned run and that the full report lives in the Research App, which implies this is a retrieval/summary step rather than the primary reading surface. There is no explicit 'use this after research_run_list returns a run_id' routing, and no when-not guidance.

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