Invoke Platform Agent Tool

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

It explains the read-only guarantee beyond the annotations: API-key credentials are restricted to registry tools with `data.read` capability, write-capable tools cannot be invoked this way, and the platform re-checks every call. It also discloses denied-capability error behavior and the shape of the response.

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 longer than average but well-structured with labeled ARGS, USE WHEN, NOT FOR, and RETURNS sections. It is front-loaded with the core behavior and stays focused; minor redundancy in the read-only paragraph keeps it from being maximally concise.

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 dynamic dispatch tool with no output schema, the description covers the API endpoint, credential constraints, argument contract, return shape, optional return fields, and error behavior. An agent has enough information to decide when to use it and how to interpret results.

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 coverage is 100%, so the baseline is 3, but the description adds meaningful context: `args` must match the target tool's input_schema, `document_ids` is a hard scope for scope-aware tools, and concrete tool-name examples clarify expected values. This goes slightly beyond the schema without fully duplicating 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 action: 'Invoke ONE named tool from the platform's agent tool registry directly, with no model in the loop.' It names concrete examples like `query_data` and `get_document_markdown`, and differentiates from the dedicated talonic_* tools by saying those are preferred for their own jobs.

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?

It gives explicit USE WHEN and NOT FOR guidance: use when `talonic_list_agent_tools` shows `can_invoke: true`, and avoid when a dedicated talonic_* tool already exists. It also tells the agent to pass exactly the `args` declared by the selected tool's `input_schema`.

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