asana_get_custom_field

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds specific behavioral detail about the response: it returns type, precision, and the fully populated enum_options list (name+GID). This goes beyond the annotations without contradicting them and gives the agent a clear expectation of the returned payload structure. It does not, however, disclose pagination or error behavior, but for a fetch-one-via-GID operation this is largely harmless given the annotation coverage.

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 a single, dense sentence with no redundant words. It front-loads the primary action and identifier, then concisely enumerates the useful response components. Every word contributes to the agent's understanding, with no filler or repetition.

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?

Given that the tool is a simple fetch of a single resource by its ID, and there is no output schema to rely on, the description covers the essential invocation material: what the tool does, what key parameter to supply (GID), and what the response will include. It does not mention any error scenarios or whether custom_field_gid is a path parameter or query parameter, but the annotation/openWorldHint and the simplicity of the operation make this adequate. The only missing piece is detailed context for the opt_fields parameter, which is already handled by the schema description. Overall, it is sufficient for an agent to call this tool correctly.

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?

The schema documents only opt_fields (50% coverage) with a detailed explanation, while custom_field_gid lacks any description. The description says 'by GID' but adds no additional semantic value about custom_field_gid (e.g., it's a required string identifier) or how opt_fields interacts with the default returned fields. The schema already explains opt_fields well, so the description contributes essentially nothing to parameter meaning. Since the unannotated custom_field_gid parameter is the primary one, this is a notable gap.

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 states the precise action (favorite 'fetch' vs 'get'), the target resource (custom field), the identifier (by GID), and explicitly lists the returned data components (type, precision, full enum_options name+GID list). This clearly differentiates it from sibling listing tools like asana_list_workspace_custom_fields and provides an agent with a complete purpose statement.

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 implies usage (fetch a specific custom field when you have its GID) but does not explicitly state when to use this tool over alternatives, nor does it mention any conditions or exclusions. It is only through the name and the sibling list that one can infer it is for individual field retrieval, not mass retrieval or manipulation. This is sufficient for a simple read operation but below the explicit bar for when/alternatives guidance.

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