compute.wait_run

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

Annotations only declare readOnlyHint, and the description adds real behavior: hard timeout bound (0-60s), a second cap from [progress].max_wait_seconds config, cache semantics at zero, and that it never mutates state. It does not say what is returned when the timeout expires with no change, which is the remaining behavioral question for a long-poll.

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 and dense with no filler sentences; every clause carries information. The telegraphic parentheticals and bracket notation ('[progress].max_wait_seconds') are slightly cryptic but cost nothing in length.

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 should indicate what a poll returns (a revision, a snapshot, or nothing on timeout) but omits it, even though after_revision makes the return shape central to correct use. Otherwise adequate for a four-parameter read 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 coverage is 0%, so the description must carry parameter meaning and largely does: timeout_seconds gets bounds, config-cap and zero-means-cache semantics; after_revision is framed as a repeat cursor. The until enum values are only echoed, leaving 'phase' and 'alert' undefined, and run_id is assumed obvious.

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 operation (bounded read-only long-poll) on a specific resource (run) and enumerates the conditions it waits for (change, terminal, phase, alert). It implicitly distinguishes itself from compute_submit_run/compute_cancel_run via 'Never submits or cancels', though it never names a sibling tool.

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?

Gives a usable polling pattern ('Not a background notification; repeat with after_revision') and notes timeout_seconds=0 reads the cache, which is genuine when-to-use guidance. It stops short of naming an alternative for one-shot reads (e.g. compute_get_run) or get_run_progress, so the agent must infer when to poll versus just fetch.

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