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

Annotations already flag destructive/non-idempotent/openWorld, but the description adds substantial context beyond them: it re-runs the monitor to confirm, documents undo:true as reverting the last fix, and discloses a version-dependent behavior shift where plugin 1.77.0+ never mutates remotely and instead returns an applyInWordPress link. That caveat is exactly the kind of side-effect detail an agent cannot get from structured fields.

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 verb and resource, and the remaining sentences each carry a distinct instruction (re-run monitor, user confirmation, undo, plugin-version behavior). It is a dense paragraph with parenthetical asides that make it slightly run-on, but nothing is 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?

For a destructive two-parameter tool with no output schema, the description covers side effects, confirmation requirements, undo, and the alternate return path on newer plugin versions. The main remaining gap is which alternative to use when a run proposes no fix, though the description otherwise leaves little an agent needs missing.

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 both parameters are already documented in the schema, and the description's undo explanation largely mirrors the schema wording. It adds the contextual point that proposedFix.why and undo should be surfaced to the user, which is helpful but not parameter-format detail. Baseline 3 is appropriate.

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 (apply) and resource (the one-click fix a run proposes), with concrete examples of what such a fix is (clearing a stuck maintenance file, re-enabling indexing, rolling back a plugin update). Naming get_run's proposedFix as the source clearly separates it from siblings like request_ai_fix and get_fix_prompt.

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 real workflow guidance: only that exact fix can be applied, tell the user why (proposedFix.why) and the undo path, and get go-ahead first. It stops short of explicitly contrasting with adjacent siblings such as request_ai_fix or start_safe_update, so the agent must infer which tool is appropriate when no run proposal exists.

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