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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower; the description adds real value by disclosing that diagnostics carry file and line, and that the handler is not built so deploy may still reject a route. That limitation is exactly the kind of nuance annotations cannot express.

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 with the primary behavior first and the important limitation second; no restatement of the name or title and 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 two-parameter, read-only compile check with no output schema, the description covers what is returned (diagnostics with file and line), what is not persisted, and where the check's authority ends. Nothing needed to invoke or interpret it 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 100%, so the properties (name, code, encoding, privateKey) are already documented, and the description adds no syntax or format detail about them. Baseline 3 applies when the schema carries the semantics.

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 (compile the submitted code) and immediately scopes it as a non-persisting dry run, which cleanly separates it from write_code, change_code, and deploy. An agent can tell what it does and does not do 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?

The phrase 'without saving or deploying' signals this is the pre-flight alternative to write_code/deploy, and the closing sentence explains the boundary case where deploy can still fail after a successful check. It gives clear context but never names the sibling tools or states an explicit 'use this instead of X' rule.

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