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

No annotations are provided, so the description carries the full burden. It discloses several behavioral traits: the tool is real-time with a short TTL, returns per-field source provenance, and can return data that differs from the stale snapshot. It also details that it surfaces live headcount/jobs/funding freshness when providers are set. It does not mention any side effects, but the tool is clearly a read-only overlay and the transparency about freshness/staleness and provenance is strong. A 4 is appropriate because it goes well beyond a generic description, though it doesn't enumerate potential edge cases (e.g., what happens when company_id is invalid or providers are not set).

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 rich but well-structured, immediately front-loading the core value ('LIVE real-time overlay') before diving into specifics. Every sentence earns its place: the staleness contrast, the ALWAYS guidance, the return-block detail, the pivot instructions, and the ancillary data mention. It is two substantial sentences with high information density and no fluff or repetition.

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?

Given the tool's complexity (real-time overlay, GOING-PUBLIC detection, data provenance, freshness nuances), the description is remarkably complete. It explains the difference from sibling tools, provides clear action guidance, details the `public_transition` return block, and mentions additional data surfaces. No output schema exists, so the description's explanation of what is returned is essential and well covered. The absence of an output schema makes the explicit return-block description even more valuable.

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 coverage is 100% and there is only one parameter, `company_id`, so the schema already fully documents the parameter. The description does not add syntax-level details but reinforces that the parameter refers to a private company. Since the schema carries the entire burden and the description provides enough context to know what the parameter represents, a baseline of 3 is met. However, the description adds the crucial context that this is for private companies specifically, which is semantically meaningful beyond the raw 'Path parameter' comment — hence a 4.

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 clearly states this is a LIVE real-time overlay for private companies, with the specific verb 'LIVE real-time overlay' and resource 'private company'. It explicitly distinguishes itself as the fast-moving complement to the weekly/possibly stale private-markets profile, and highlights its key purpose: checking whether a private company has GONE PUBLIC. It also lists the specific return block (`public_transition`) with concrete fields (ticker, IPO date, SEC evidence), making it unmistakable versus siblings like `tengu_v3_private_markets_company` or `tengu_v3_private_markets_company_dossier`.

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 gives explicit, imperative usage guidance: 'ALWAYS call this for a private company to check whether it has GONE PUBLIC'. It also provides a conditional action path — if `public_transition` is returned, 'then pivot to the public-equity tools (price_snapshot / company_facts / sec_filings)'. This both states when to use the tool and provides explicit alternatives/next steps, going beyond simple context into actionable workflow.

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