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

Annotations already establish read-only, non-destructive, non-open-world behavior, so the bar is lower. The description goes further by guaranteeing secret values are never returned by any tool and by explaining the {{secret:NAME}} server-side substitution model, which prevents an agent from expecting retrievable secrets. It does not describe the response shape (allow-list format), a minor gap.

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-loads the primary deliverable (names + allow list) and keeps to three tight sentences. The {{secret:NAME}} substitution sentence is slightly tangential to a listing tool but serves a real purpose in setting expectations about how secrets are consumed.

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 carries the return-value burden and does so well (names, allow list, no values). It covers safety, scope, and usage intent; only a brief note on the response structure for the allow list is 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?

Only one parameter (title_id) with 100% schema description coverage, so the schema carries full documentation. The description implies the title scoping ('the title's') but adds no new detail about the parameter beyond what the schema provides, making the baseline of 3 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?

Specific verb (list) plus precise resource: the NAMES of a title's integration variables/secrets and the outbound-HTTP allow list. It explicitly scopes what is returned (names, not values), which cleanly distinguishes it from get_cloud_code and the save_* siblings. An agent can identify the tool without opening 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 a clear when-to-use rationale: 'Use this to discover which credentials a title already has before writing an integration.' This gives concrete context for invocation but names no alternatives or exclusions (e.g., where to manage secrets once discovered), so it stops short of full routing guidance.

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