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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, and the description adds substantial context on top: selection is deterministic and does not use a language model, and it details the exact shape of the result (ask_first first, one recommendation workflow, at most two alternatives, plus an internal evidence section). This goes well beyond what the annotations convey.

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?

One dense paragraph, front-loaded with purpose before mechanics and the general_question special case. Every sentence carries information (deterministic model, output ordering, edge-case task), though the middle sentence stacking recommendation sub-parts is somewhat heavy.

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?

There is no output schema and the nested properties object holds ~32 fields, so the description carries real burden; it compensates by describing the return structure (ask_first, recommendation, alternatives, internal ids/evidence/sources) and the special general_question path. An agent has enough to call it correctly and interpret the response.

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 the baseline is 3, but the description adds meaning beyond the schema by explaining the interaction between description, task and properties ("the process properties it states; leave out what it does not say") and clarifying the special semantics of general_question and user_unsure. Marginal but genuine added value over the already-thorough schema.

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: advises on using AI in a user-described process, drawing from a curated, sourced knowledge base. It distinguishes itself from siblings like adoption_get_pattern by describing the input (free-text description plus matched task and properties) and the deterministic selection model, so an agent can tell this is the entry-point discovery 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 clear routing context: use task general_question when there is no concrete process, and set user_unsure true after the user says they don't know. It does not, however, explicitly name sibling alternatives (e.g., use adoption_get_pattern to fetch one pattern by id, or adoption_list_process_types to browse), leaving that comparison to inference.

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