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

Annotations already declare destructiveHint=true and idempotentHint=true, but they cannot say what is destroyed versus preserved. The description fills exactly that gap: only the session link is removed and the study stays available in User Intuition. It omits authorization/membership requirements, which keeps it 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?

A single well-formed sentence with the action front-loaded and the crucial non-destructive caveat in the second clause. No filler, nothing repeated from the title or schema.

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 two-required-parameter mutation with full annotations and an output schema, the description covers the main behavioral question (what survives). Remaining gaps — behavior when the study is absent from the session, or when the session is closed — are minor rather than blocking.

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 33% — only organization_id carries a description (pointing at list_organizations). The description implicitly maps session_id and study_id through phrasing ('one study source from a Hub session') but adds no semantics such as whether the study must already be attached or what happens on an unknown ID. Baseline 3 for a low-coverage schema that the description does not compensate for.

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 (remove) and resource (one study source from a Hub session), and explicitly clarifies that the underlying study persists, which separates it from delete_study. It does not name the closer siblings (remove_research_source, clear_research_sources), so an agent still has to infer the boundary between 'study source' and 'research source'.

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?

The sentence implies when this applies — detaching a single study from a session without destroying it — but never states explicit alternatives or preconditions. With siblings like clear_research_sources (bulk) and remove_research_source (different resource name) in the same family, an explicit contrast would materially help selection.

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