get_pattern_topology

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states 'Does not mutate the MD scene,' which is a clear read-only declaration. It also discloses that ambiguous mappings are never guessed, implying it may error or request clarification rather than silently misresolve, and that stale references require re-reading. These are meaningful behavioral traits that go beyond the minimal requirements. It does not cover error codes or response format, but the provided transparency is strong.

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 a single dense run-on sentence, packed with information but not well-structured. It starts with a cryptic feature list, then moves to usage and behavior. While it is not excessively long, the lack of clear separation between purpose, usage, and behavior reduces readability. The content is efficient but the organization is poor, making it harder for an agent to parse quickly.

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 that likely returns a complex topology structure, the description is incomplete. It mentions 'native point/line enumeration' and 'geometry snapshot refs' but does not explain the structure of the return value, how the refs should be used, or what 'topology' means in this context. There is no output schema, so the description carries the responsibility of describing the result. It also omits error handling and edge cases. The description provides some context but leaves critical gaps that an agent would need to resolve.

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?

The schema provides a single parameter 'pattern' as either integer or string with zero description coverage. The description fully compensates by explaining that it can be a UUID (string), a unique name (string), or a freshly inspected index (integer). It also clarifies the notion of 'freshly inspected' implying the index must come from a recent list operation. This adds substantial semantic value beyond the schema, giving the agent clear guidance on how to construct the parameter correctly.

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 does not clearly state that this tool retrieves the topology of a pattern. It lists features like 'UUID + native point/line enumeration + geometry snapshot refs' without defining what 'topology' means or what the output represents. The verb 'get' is implicit in the name, but the description reads as a feature list rather than a purpose statement. It is not a tautology, but it is vague and cryptic, leaving the agent uncertain about the exact resource being returned.

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 offers some usage context: it explains how to select the pattern (by UUID, unique name, or freshly inspected index) and advises preferring stable refs for edits. It also mentions 'Read again after STALE_REFERENCE', which hints at when to re-invoke. However, it does not explicitly compare to sibling tools like get_pattern_points or get_pattern_info, nor does it state conditions for when to choose this tool over alternatives. The guidance is implied but not explicit.

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