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

With no annotations present, the description carries the full burden and does well: it discloses that the secret is encrypted at rest and never returned, that config/secret are schema-validated per kind, and that (kind,label) must be unique per account. It omits auth/permission requirements and error behavior, so it is strong but not exhaustive.

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?

Two dense sentences, front-loaded with the core definition and followed by constraints. Every clause carries distinct operational information (catalog source, validation, encryption, uniqueness) with no filler.

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?

For a mutation tool with no annotations and no output schema, the definition covers creation semantics, validation inputs, and the sensitive-data behavior ('never returned'). It stops short of stating permission requirements, failure modes, or what a successful create returns, which leaves a modest gap.

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 already 100%, so baseline is 3, but the description adds semantics the schema lacks: the catalog source and validation rules for `kind`, per-kind schema validation for `config`/`secret`, and the cross-field uniqueness constraint on (kind,label). That is genuinely additive constraint information rather than restatement.

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 names a specific verb+resource and goes further by defining what a connector is ('an encrypted credential a skill can use'), which lets an agent distinguish it from unrelated create_* siblings like create_report or create_skill. It is clear but does not explicitly contrast with any adjacent tool beyond pointing at list_connectors.

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?

It gives a concrete prerequisite: `kind` must come from the catalog kinds exposed by list_connectors, and config/secret are validated against that kind's schema, which effectively routes the agent through list_connectors first. There is no when-not guidance, but there is no true alternative to this tool among the siblings.

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