pmg_what_object_add

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

No annotations are provided, so the description carries full burden. It discloses the mutation type (LOW), dry-run behavior, confirmation requirement, and config prerequisites. It also explains type-specific fields and parameter mappings, which adds significant behavioral context beyond just 'add an object'.

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 dense but well-structured, starting with purpose, mutation type, usage, API path, and parameter details. Every sentence adds value, though the length is justified by the complexity (11 parameters, type-specific fields). It earns a 4 for being appropriately sized without wasted words.

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 the complexity (11 parameters, 2 required, no annotations, but has output schema), the description covers the core functionality, usage instructions, parameter details, and special mappings. It doesn't describe the output or potential errors, but the output schema exists for that. Overall, it is fairly complete for an agent to invoke 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?

Schema description coverage is only 9%, but the description adds detailed semantics for most parameters: ogroup (numeric from pmg_what_groups_list), type_ (list of valid values), and type-specific fields like contenttype+only_content, field+value+top_part_only, etc. It also explains parameter mappings like only_content -> 'only-content' and top_part_only -> 'top-part-only', fully compensating for the low schema coverage.

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 specifies the action: add an object to a PMG RuleDB 'what' object group. It includes the API path, the required ogroup and type_, and distinguishes this from siblings like pmg_what_object_delete or pmg_what_object_update.

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 explains the dry-run default and confirm=True to execute, plus the need for PROXIMO_PMG_* config. However, it does not explicitly state when to use this tool versus alternatives like pmg_what_object_update, though the context is implied.

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