diff_assembly_manuals

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

With no annotations, the description carries the full burden, and it does disclose one genuinely useful behavioral fact: the Business-tier requirement and that it writes a PDF output. It does not say whether the call is read-only, whether output_pdf_path is written to disk, what happens when a revision is missing, or whether the diff is against released or draft state.

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 core sentence is front-loaded and efficient, but two of four sentences are upsell copy ('Business adds team review, approval gates, and 3 printers', plus a pricing URL). The tier requirement is worth one clause; the feature tease and link do not earn their place.

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 tool with 16 all-optional identifier parameters, no annotations, and no output schema, the description is far too thin. An agent cannot tell how to construct a valid diff request, what the output artifact is beyond 'a PDF', or under what conditions the call fails on licensing.

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 13% (only two booleans have 'Default: false'), and the description adds no parameter meaning at all. For a 16-parameter tool with zero required fields, the agent is left guessing which identifier family forms a valid call, which is exactly the gap the description should have closed.

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 first sentence gives a specific verb and resource: 'Compute a "what changed" PDF between two manual revisions.' That is unambiguous. However, it never distinguishes itself from nearby manual tools (get_manual_revision, list_manual_history, generate_assembly_manual, find_manual_siblings), so an agent still has to infer why it should diff rather than generate or fetch.

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 only guidance is the tier gate ('Requires Kiln Business'). There is nothing on when to diff versus regenerate or list history, and nothing on which of the 16 mutually-substitutable identifier parameters (manual_id_*, version_id_*, release_id_*, spec_*_path, assembly_*_json) to supply in which situation.

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