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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description goes well beyond them: it discloses the return shape (reviewed runbooks plus matched query words), the epistemic caveat that runbooks are guidance not proof, and a detailed data-handling disclosure covering exactly which call arguments are stored, that account keys are one-way hashed, that billing and validation sources are excluded, that IPs are never stored, and what exit tools log. This is unusually rich behavioral context for a search tool.

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?

Purpose and routing are front-loaded in the first two sentences, and the privacy disclosure is dense but relevant to a tool that stores arguments. The clause about exit tools logging result counts is somewhat tangential to this search tool and adds length without helping an agent invoke it, keeping it short of a 5.

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 must describe returns, and it does: reviewed runbooks with the query words they matched, plus the pointer to get_workflow_recipe for full content. It also covers the data-governance obligations an agent needs to know before sending arguments (no personal data or secrets). Nothing material is left for the agent to infer.

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 67%: 'query' and 'vendor' are documented in the schema, while 'limit' is not. The description adds only that results come 'with the query words they matched', which hints at matching behavior but gives no extra syntax, format or constraint detail beyond the schema. 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?

Opens with an explicit use scope ('a whole operational change rather than one subscription') and backs it with concrete examples (shared billing, moving hosting or email, retiring a dormant project, model routing, queues, auth, storage). It also explicitly distinguishes itself from the sibling get_workflow_recipe, which returns one recipe in full, so an agent can route correctly without reading 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?

States when to reach for this tool (whole operational change, not a single subscription), names the alternative tool for the follow-up step (get_workflow_recipe returns one in full), and warns that runbooks are guidance rather than proof a migration ran. When-to-use, when-to-escalate and the caveat are all present.

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