pid

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

Annotations only declare readOnlyHint=false, which the description's mutating operations (setup_layers, insert_symbol, etc.) align with; no contradiction. However, the description does not disclose side effects (e.g., whether setup_layers clears existing layers, how insert_symbol interacts with the symbol library, or transaction requirements). It adds little behavioral context beyond the annotation's mutation hint.

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 and well-organized: a one-sentence purpose followed by a compact, sorted operation list with required data fields. Each line is necessary for an agent to invoke the tool; there is no redundant prose. The front-loaded purpose is good. The length is justified given the tool's multi-operation nature.

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?

This is a complex tool with 8 parameters, no output schema, and a multi-operation dispatch model. The description fails to explain what the tool returns (e.g., whether it returns an entity ID, success status, or screenshot), how doc_id and lease_token affect operations, or which operations require an existing document. These gaps leave an agent without critical operational context.

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?

With 0% schema coverage, the description compensates effectively by specifying the data payload structure for each operation (e.g., data: {category, symbol, x, y, scale?, rotation?}) and enumerating valid operation values. This adds meaning the input schema entirely lacks. However, it omits semantics for generic top-level parameters like doc_id, lease_token, and idempotency_key, and the operation values are not formal enums.

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 opening sentence 'P&ID drawing with CTO symbol library' clearly establishes the domain, and the detailed operation list (insert_symbol, draw_process_line, insert_valve, etc.) specifies concrete capabilities. This distinguishes it from sibling tools like generic drawing or layer by focusing on P&ID-specific symbols and workflows. However, it lacks a single, direct statement of what the tool as a whole does, relying instead on the enumerations.

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 provides no guidance on when to use this tool versus alternatives among sibling tools (e.g., drawing, layer, annotation). It does not state exclusions or preferred contexts. The operations imply usage but do not explicitly contrast with other tools, leaving the agent uncertain about the boundary between pid and more generic drawing tools.

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