Get terms on content

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it clarifies the output is not just IDs but fully resolved term objects, and that results are grouped by taxonomy. This gives the agent expectations about the return structure, which is useful for post-processing. It does not mention pagination or potential errors, but for a read-only grouped fetch, this is adequate.

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, concise sentence that front-loads the primary action and key detail (grouped, resolved to full term objects). It avoids unnecessary words and is easy to scan. The only minor issue is that it could mention the 'type' parameter's role more explicitly, but that is covered in the schema. Overall, it is well-structured and 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?

For a read-only, single-item fetch with no output schema, the description is sufficiently complete. It tells the agent what to expect in the response (full term objects grouped by taxonomy) and what the tool does. It does not document edge cases (e.g., no terms assigned) or required permissions, but given the read-only nature and simple parameter set, this is adequate. The schema covers all parameters, so no gaps remain.

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 each parameter (type, site_id, content_id) has a clear description in the schema. The tool description adds value by explaining the semantics of content_id (the content item to inspect) and the overall purpose. The description also clarifies that the response includes full term objects, which is not in the schema. The schema already explains site_id's behavior well, so the description does not need to repeat it.

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 a specific verb ('Get'), a clear resource ('taxonomy terms on one content item'), and specifies the output format ('grouped by taxonomy', 'resolved to full term objects'). It clearly distinguishes this from sibling tools like assign_terms_to_content, which does the opposite operation (assignment), and from list_terms/get_term which list or fetch terms independently without linking to content. An agent can easily understand what this tool does and what it returns.

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 the tool is for reading terms on a single content item, but it does not explicitly state when to use this versus alternatives like list_terms or get_content_meta. The presence of sibling tools like list_terms suggests one could retrieve all terms in a taxonomy, but the description does not compare or contrast. Given the broad tool set, more explicit routing would be helpful, but the core use case is clear enough from the purpose.

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