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

Annotations already establish readOnlyHint=true, destructiveHint=false, openWorldHint=false, so safety is covered; the description goes further by disclosing domain behavior the annotations cannot: status and charge are independent (a FAILED run can carry a non-zero charge), run_url resolves to provider-returned records in the workspace console, access is 'members only', and citation of run_url is required because the run id alone opens nothing. That is substantive added context on auth and result semantics.

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 returned fields, followed by the two non-obvious behavioral facts (failed-but-charged, cite run_url), then a docs link. Dense and every clause carries information; no filler.

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 no output schema, the description takes on the burden of enumerating return fields and does so explicitly. Combined with the read-only annotations, an agent has everything needed to call this correctly and interpret the result, including the citation requirement.

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 0%, so the schema gives only the type/format (uuid pattern) without prose. The description partially compensates by naming the parameter's role ('by run_id') and clarifying that the id alone opens nothing, but it never explains where a run_id comes from or its expected form. Marginal value over the structured fields.

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 ('Get one run by run_id') and enumerates exactly what comes back (status, output, provider_response, failure, charge_usd, charge_basis, run_url), which is enough to distinguish it from runs_list (plural/summary) and runs_stop (mutating). An agent can identify the tool without opening the schema.

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: fetch a single run when you already hold a run_id ('Get one run by run_id'). There is no explicit routing guidance telling the agent to use runs_list or search first to obtain a run_id, and no when-not condition. Adequate but inferential rather than explicit.

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