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

Goes well beyond the annotations by disclosing the auth requirement (organisation token, 'Authorization: Bearer hodds_...') and the exact failure mode ('token_required' when absent). It also states the anonymity threshold governing what is aggregated and explicitly what is NOT returned (no need text, no organisation, no agent), which is meaningful behavioral context the annotations do not carry. It stops short of describing result volume or pagination.

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 scope, then the payload list, then auth — a sensible ordering with no filler sentences. The 'Contract 0.3.1' string is the one element of dubious value for an invoking agent, and the parenthetical list is dense but each item carries information.

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?

An output schema exists, so the field enumeration is redundant but harmless; the essential gaps an agent would have — auth requirement, failure mode, prerequisite of subscription, what is excluded from results — are all covered. It does not explain what 'subscribed' means operationally or whether results are bounded/paginated, which keeps it from a 5.

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% and the single enum parameter is fully documented in the schema as a process id from /catalogue/processes.json. The description adds only the 'subscribed process' qualifier, which is a constraint rather than new meaning about the parameter itself, so the baseline 3 applies.

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 a concrete verb and resource ('Returns ... the gaps') scoped to a subscribed process, then enumerates the payload categories (watched needs, NO_MATCH, current choices, constraints, challengers delivered). This is clearly distinct from siblings like list_processes or list_watches, though the heavy internal jargon (HODDS, NO_MATCH, GAP_RESOLVED) is not defined for an outside agent.

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?

The phrase 'for a subscribed process' implies the precondition that the caller must already be subscribed, which is useful routing context. However, no sibling is named and there is no explicit when-to-use/when-not guidance versus list_watches, get_watch, or list_processes — the agent must infer that this is a read of derived demand data.

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