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

Annotations already declare readOnly, idempotent, non-destructive, so credit goes to the extra disclosures: the API is a preview that may change without a version bump, requires services:read authorization, and deliberately strips free-text descriptions from results. That is real behavioral context an agent cannot get from the annotations.

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?

A single dense sentence-cluster with no filler: return payload first, then omissions, then permission, then stability. Every clause carries distinct 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?

Covers permissions, payload shape, and stability, but for a 4-parameter list tool with 25% schema coverage and no output schema, it leaves pagination behavior and the resourceId filter under-explained. Adequate but with clear gaps.

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 only 25% (just 'after' documented), so the description should compensate. It hints at resourceId semantics via 'per-resource overrides' but never explains that resourceId scopes the catalog, nor clarifies limit defaults or that 'after' is the pagination cursor for this endpoint (the schema text oddly references stock movements).

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?

Names the resource (service catalog) and enumerates the returned data precisely: durations, prices, VAT, per-resource overrides, and explicitly what is omitted (free-text descriptions). It does not distinguish itself from nearby siblings such as list_resource_services or list_service_groups, so an agent must infer that this is the full-catalog variant.

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 only usage context given is the required 'services:read' scope and the 'Preview API' framing; there is no statement of when to choose this over list_resource_services or list_service_groups, nor when resourceId filtering is appropriate. The agent gets a prerequisite but no routing guidance.

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