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

Annotations only disclose readOnlyHint=false, destructiveHint=false, openWorldHint=true. The description goes well beyond that: it explains that validation can reject packages and name alternatives, that versions may be pinned/substituted, that installs run on the project VM and persist resolved versions, and that slow installs complete asynchronously as a job requiring a follow-up call.

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 paragraph, but front-loaded with the core action and every sentence carries a real constraint or quirk. It is longer than typical, though the detail is substantive rather than 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 output schema, the description covers the critical async job pattern, persistence behavior, validation/alternative-naming, and version resolution. An agent has what it needs to call this correctly and follow up.

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 0%, so the description must carry parameter meaning. It explains `packages` semantics richly (bare vs `kysely@<version>` syntax, substitution behavior), but `projectId` is never mentioned, leaving one of two params undocumented. Strong on the non-obvious param, silent on the obvious one.

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?

States a specific verb and resource: 'Add npm packages to the project,' and immediately scopes it with validation and version-pinning behavior. An agent can distinguish this from remove_dependency and the file-editing siblings 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?

Gives explicit when/when-not guidance: avoid node-gyp/native packages, WASM, and large binaries; prefer pure JS/TS; the sharp exception. It also states when to pass an explicit `kysely@<version>` versus a bare `kysely`, and prescribes the two-call retry flow for slow installs.

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