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

Annotations already indicate readOnlyHint=false and destructiveHint=true, but the description adds valuable behavioral detail: only local Connections MCP sessions, Studio console sessions, or cnx_live_ keys receive `values`, while assistant sessions only get `valuesWithheld`. It also explains the `describeOnly` mode's effect on the response. It does not elaborate on why the operation is marked destructive, but the added context still exceeds what structured annotations alone provide.

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?

The description is dense and front-loaded with the core purpose, then provides necessary security and response-shape context. It is a long single block of text, which hurts skimmability, but nearly every clause adds useful information and none is redundant with the schema.

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 compensates by specifying the reply shape: `{service, instance, accountId, fields[], hints{}, primary}` plus `values` conditionally. It also covers the most important contextual constraints, such as which client types receive values. Minor gaps remain around lease lifecycle or destructive side effects, but the essential decision-making information is present.

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 core parameter definitions exist. The description enhances them by explaining that `service` is a connected-service slug valid across all supported services, that `instance` supports AWS account IDs, and that `describeOnly: true` changes the response to field names and masked hints rather than values.

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?

The description opens with a specific verb and resource: 'Return THIS company's stored credential for a connected service so a LOCAL script or vendor CLI can act with it.' It also differentiates itself from bespoke per-service tools and details the universal scope ('aws, stripe, cloudflare, github, twilio, openai').

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 description clearly explains when to use the tool: for local scripts or CLIs that need a stored credential, and for describe-only mode when planning env vars. It names the usual integration path (local MCP's shell/script_run via their secrets parameter) but does not explicitly contrast it with specific sibling tools or give negative usage criteria.

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