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

With no annotations provided, the description carries the full burden of behavioral disclosure and succeeds. It reveals idempotency ('storing a key you already have returns the existing one instead of creating a duplicate'), that authentication is required, that it is safe to call repeatedly ('safe to call before every order'), and what it returns (the key id). This is precisely the behavioral context the absent annotations would otherwise need to supply, and there is no contradiction.

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?

Five short sentences, each carrying distinct information: purpose, idempotency, authentication, required parameter formats with examples, and return value. The structure is front-loaded with the core purpose, and no sentence is redundant with the schema — even the 'Required:' repetition adds examples the schema lacks.

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?

Despite having no annotations and no output schema, the description covers the full call contract: what the tool does, authentication requirements, both required parameters' semantics and formats, idempotent behavior, the return value (key id), and how to use it downstream. Nothing an agent needs to invoke it correctly 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?

Schema description coverage is only 33% — only sessionKey has schema documentation, while the two required parameters have none. The description compensates for this gap by defining name as 'a label, e.g. laptop' and publicKey with its required format and an example ('single-line OpenSSH public key, e.g. ssh-ed25519 AAAA... user@host'). It leaves sessionKey to the schema, which already documents its auth-flow-dependent behavior, so compensation is complete but not exhaustive.

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 states a specific verb and resource — 'Store an SSH public key on your account' — and adds its purpose ('so it can be injected into VPS installs'). It is clearly distinguishable from sibling key tools like deleteShKey and listMySshKeys, and the return-value tie to orderVps/buildVpsInstance reinforces what this tool is for.

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 gives explicit when-to-use guidance: 'safe to call before every order' and explains the downstream integration (pass the returned key id to orderVps or buildVpsInstance). However, it does not explicitly name sibling alternatives (e.g., listMySshKeys, deleteSshKey) or state when not to use this tool, stopping short of a 5.

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