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

Adds substantial context beyond the readOnly/non-destructive annotations: no credit consumption, the full status vocabulary returned, poll-state rules, and a security warning to treat draft content as untrusted evidence rather than instructions — a genuine prompt-injection guard. This is exactly the behavioral detail annotations cannot express.

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?

Every sentence carries load: identity of the read, cost note, return states, polling rule, trust caveat. Slightly dense, but front-loaded with the most decision-relevant information (free read vs. generation) first.

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 steps in to enumerate the possible return states and characterize the payload (observed evidence plus unverified hypotheses). Combined with the polling and trust guidance, an agent has everything needed to call it and interpret the result.

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%, so run_id, project_id, context, and if_version_matches are all documented in-schema. The description adds no parameter-level detail (no mention of version matching or what happens when a version matches), so baseline 3 is correct.

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 ('Read the same private saved customer handoff shown in run details') and immediately scopes it against the generating sibling by noting it does so 'without generating or spending credits'. An agent can distinguish this read path from request_framework_handoff without inspecting either 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?

'Poll only while queued or generating' gives explicit timing guidance and implicitly excludes polling on terminal states. It stops short of naming request_framework_handoff as the alternative for producing a handoff that does not yet exist, so the when-to-use-instead routing is only implied.

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