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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses a per-agent daily free-tier cap with the exact error code (free_tier_cap_reached) and reset timing (00:00 UTC), plus three named structured-error conditions returned rather than raised. It also explains that there is no purchase path, so agents won't hallucinate an upsell step. That is precisely the behavioral context annotations cannot carry.

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 purpose and coverage requirement are front-loaded, which is good, but the middle paragraph is internal product-death provenance — a verbatim chat quote, an order-document path, and a discussion of a killed paid product — that does not help an agent invoke the tool. The one operationally useful fact there (the free tool still exists, there is nothing to buy) could be a single clause.

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 an output schema present, return values need no explanation, and the description closes the remaining gaps: preconditions (coverage universe, current-period data), rate limiting, and all failure modes with error codes. The only soft spot is that it never says how an agent can test whether a ticker is in coverage before spending a call.

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 description coverage is 100% — ticker, optional fiscal year with default, and agent_token with header fallback are all documented inline. The description adds nothing about parameter format or interactions, so baseline 3 applies.

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 first sentence gives a specific verb+resource ("Generate a Governance Alpha Card") and the second enumerates its contents (pay alignment, governance scorecard, SoP risk band, peer quality, risks/strengths), so an agent knows this is a composite per-company report generator. It does not explicitly distinguish itself from near-neighbors such as predict_say_on_pay_risk or get_company_compensation, which keeps it below a 5.

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?

"Requires the company to be in Velarion's coverage universe with current-period data" plus the error list implies when the tool is usable, and the free-sample framing hints at a lightweight alternative to the paid product. However, there is no explicit instruction on when an agent should reach for this card instead of the sibling lookup tools, or how to verify coverage before calling (e.g. via search_companies).

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