get_semantic_map

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

With no annotations, the description carries the full disclosure burden, and it does add meaningful behavioral content: the output is deterministic, candidates route to review only, and semantic equivalence is never asserted. These constraints shape expectations about stability and scope. It stops short of stating whether the tool is purely read-only or whether routing produces side effects, which prevents a 5.

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 compact at two sentences with no filler, and the core resource is front-loaded ahead of the behavioral caveat. However, the phrasing is cryptic—a noun-phrase fragment with undefined terminology—which keeps it from being an exemplary structure.

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?

The zero-parameter signature makes invocation trivial, but there is no output schema and no annotations, so the description must stand alone in explaining what the tool returns. It never describes the return value's shape or structure, and core concepts like lexical neighborhoods, supersession edges, and candidates are left undefined. An agent could call the tool but would be guessing at how to interpret the response.

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 input schema is empty and the parameter count is zero, so the schema already fully describes the input surface. Per the zero-parameter baseline, no parameter-specific documentation is needed. The description adds useful context about the resource's contents, but the absence of parameters means there is no additional semantic burden to meet.

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 identifies the resource (deterministic lexical neighborhoods and declared supersession edges) and a behavioral constraint (candidates are for review only, not equivalence assertions), but it reads as an invariant statement rather than a functional specification. It lacks an explicit verb such as 'returns' or 'retrieves', and key terms like 'candidates' and 'supersession edges' are undefined. It also does not distinguish itself from sibling tools.

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?

No guidance is given for when to call this tool, what questions it answers, or what prerequisites apply. The sibling tools are visible in the context, but the description references none of them and provides no selection criteria. The implied 'review routing' purpose is too weak to route an agent to this tool over alternatives like get_semantic_reviews.

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