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

Annotations only say readOnlyHint=false, destructiveHint=false, idempotentHint=false, which tell the agent little. The description carries the burden and does it well: it discloses the cross-board guard, the exact error_type returned (CROSS_BOARD_TEMPLATE), the recommended fallback, the best-effort board resolution behavior, and the allow_cross_board escape hatch. This is rich behavioral context beyond the annotations.

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 front-loaded with the core action and default behavior, then layers the cross-board guard and fallback. It is somewhat long but every sentence earns its place: the cross-board behavior is essential for correct invocation and cannot be inferred from the schema. The structure (default → exception → override) is logical.

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 4-parameter tool with no output schema, the description covers the key decision points: scope selection, cross-board blocking, fallback routing, and override flag. It doesn't describe the success return value or what happens on a successful attach, but the absence of an output schema and the strong behavioral coverage make this a minor gap rather than a critical one.

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 0%, so the description must compensate. It explains item_id semantics (0/omitted = workflow-level, real item_id = specific item), allow_cross_board semantics (deliberate override), and the meaning of template_id/envelope_id implicitly through the workflow context. It doesn't spell out envelope_id's format, but the required-parameter names are self-explanatory and the behavioral context is strong.

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 opens with a specific verb+resource: 'Attach an existing template gallery template to a workflow.' It then clarifies the default scope (workflow/envelope level) and distinguishes the item-level case. This clearly differentiates it from siblings like getsign_duplicate_template_for_workflow and getsign_list_template_gallery.

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 gives explicit when-to-use guidance: omit item_id (or pass 0) for workflow-level, only pass a real item_id when the user explicitly names a specific item. It also names the alternative tool (getsign_duplicate_template_for_workflow) and the exact condition (cross-board block) that should route to it, plus the deliberate override (allow_cross_board=True).

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