set_config

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

Without annotations, the description carries the full burden. It discloses that writing mutates state (write to file), that it merges with existing config (not overwrite), and categorizes keys as code-generation vs runtime. This provides useful behavioral context beyond the 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 three sentences, front-loaded with the purpose, and contains zero filler. Every sentence adds unique value: action+merge behavior, code-generation keys, runtime keys. Highly efficient.

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?

The description covers purpose, merge semantics, and key categorization. Given a single nested parameter and no output schema, it addresses the main concerns. However, it lacks guidance on error cases (e.g., invalid config) and does not confirm what the tool returns (though likely void). Still, it is adequate for the complexity level.

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?

With 100% schema coverage, baseline is 3. The description adds significant meaning by grouping parameters into code-generation and runtime categories, which clarifies the role of each key. This organization helps the agent understand which parameters matter for different stages, exceeding what the standalone schema descriptions provide.

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 that the tool writes connector configuration to a specific file (.glean/config.json) and merges with existing config. It distinguishes from siblings like get_config (reading) and build_connector (code generation) by specifying the action and resource.

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 asserts that the tool is used to write and merge configuration, but does not explicitly state when to use it vs alternatives (e.g., when to use set_config versus get_config or other write tools). Usage is implied from context, but no direct guidance or exclusion is provided.

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