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

Annotations already establish safety (read-only, idempotent, non-destructive), so the bar is lower. The description adds meaningful behavior: it accepts the two IDs in either order, returns the computed match only conditionally ('if the graph has one'), includes a confidence label, and explicitly commits to returning facts rather than a score. No statement contradicts 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 wastes no words; the opening scope clause is front-loaded and the enumerated sections carry the burden of explaining outputs. The ALL-CAPS headings are slightly telegraphic but each item adds a distinct piece of information, and the closing one-liner reinforces the tool's 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?

With no output schema, the description must carry the return-value burden, and it does: it names all major output sections and even supplies sub-details such as 'dated investments in the same sector, with sources' and 'a path on the graph if one exists.' It doesn't cover edge cases (e.g., invalid pairings) or the exact shape of the computed match/confidence label, but those are minor against the level of detail provided.

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 fully documents the ID formats for both parameters, so baseline is 3. The description adds semantic value by assigning roles (one is an investor, the other an opportunity) and by stating that order does not matter. This is information the schema alone does not convey.

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 defines the tool's scope precisely: it takes an investor-opportunity pair and enumerates the exact content returned — match reasons, blockers, supporting observations, comparable history with dates and sources, relationships, recent events, computed match (when present), and confidence label. The phrase 'Facts, not a score' clarifies what the tool deliberately does not provide. Though the verb is implied by the name/title rather than written out, the purpose is unambiguous.

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?

There is no explicit guidance on when to choose this tool over the many related siblings, such as relationship_path, get_capital_paths, or find_opportunities_for_capital. The intended use is strongly implied by the title and parameter semantics ('for an investor and an opportunity'), but the description doesn't state exclusions or alternatives. This keeps it at implied rather than explicit guidance.

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