codeql_update_file

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. It explicitly indicates the file must be open, that the entire content is replaced ('New complete content'), and that changes are unsaved (implying no persistence). It also discloses the return type (dictionary with success message and metadata). While it omits error handling and persistence nuances, it provides substantial behavioral context beyond the bare schema.

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?

The description is well-structured and concise: a clear purpose sentence, one contextual sentence, a brief args list, and a return note. Every line contributes meaningful information with no redundancy or vagueness, making it easy for an agent to parse quickly.

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 simple two-parameter update tool with an output schema, the description covers the essential aspects: purpose, usage context, parameter semantics, and return value. It does not explain error conditions or detailed side effects, but these are relatively minor for this straightforward operation and do not impede correct invocation.

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?

Since schema description coverage is 0%, the description must compensate. The Args section defines file_uri as 'URI of the CodeQL file' and content as 'New complete content of the file,' adding essential meaning beyond the basic type annotations. This adequately explains both parameters, though it could be more specific about URI format or content encoding.

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 clearly states the tool's function: 'Updates the content of an open CodeQL file in the language server.' This identifies the specific verb (updates), the resource (CodeQL file), and the context (open file in language server), which differentiates it from sibling read-only tools like codeql_hover and codeql_diagnostics.

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 'Allows dynamic modification and analysis of unsaved changes' provides clear contextual guidance for when to use this tool—when working with unsaved, in-memory file states. It does not explicitly state alternatives or when not to use it, but this context is sufficient given the sibling tools are all read-only analysis operations.

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