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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-structured context: no account or token is required, and 'extends'/project files are not resolved — the latter being the most important behavioral caveat for a config validator.

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-loaded with the core action, then cleanly separated into when-to-use, notes, and an example — easy to scan. The example arguments partly restate a shape the schema already fully documents, which is mild redundancy, but the overall length is proportionate.

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 an output schema present, the description needn't detail return values, and it still signals that compiler diagnostics with references come back. All the caveats an agent needs to call this correctly — pinned versions, no auth, no 'extends' resolution — are 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 baseline would be 3. However, the schema's own description for 'typescript' defers to the description ('Exact TypeScript version from the list above'), meaning the actual allowed value set lives only in the description. The example arguments also clarify that 'config' may be given as a JSON object.

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 ('Validate a standalone tsconfig') plus the exact scope: a pinned TypeScript compiler version drawn from a fixed list, returning the compiler's own diagnostics. The version list and the 'standalone' qualifier make it clearly distinct from sibling validators such as validate_package_json.

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 'When to use' line gives concrete triggers: a tsconfig option being rejected, or needing to know whether an option exists in a given version. It also names a hard boundary ('extends' and project files are not resolved), which prevents misuse. It stops short of naming a sibling alternative, so it lands at 4 rather than 5.

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