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

Annotations already declare this as a read-only, idempotent, non-destructive, non-open-world operation, so the safety profile needs no restatement. The description adds genuine behavioral context beyond that: a provenance guarantee ('nothing is estimated') and the disclosure of access gating (public deal, VC-backed work-email check, investor networks) that explains why some offers appear restricted. It stops short of describing pagination or response shape, but the added value is real.

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 tool's scope is front-loaded in the opening phrase, which is good. But the definition is one sprawling sentence built on a long nested parenthetical listing every field and access mode, which is dense to parse and repeats what the schema and annotations already establish.

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 single-parameter, no-output-schema read tool, the description does the heavy lifting: it explains what the page contains, where the numbers come from, and how to get a listing instead. Only the sibling differentiation and any return-shape expectations are missing, which are modest gaps at this complexity.

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 the single slug parameter already enumerates all four valid page names and the empty-to-list behavior. The description's parenthetical re-describes the same page variants without adding format details such as URL handling rules beyond the schema's 'or the page URL'. Baseline 3 is appropriate when the schema carries the parameter semantics.

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 states precisely what is retrieved: a full startup deals page covering AI credits, cloud credits, developer tool credits, or the aggregated startup-deals listing. The verb is implicit (it's a 'get' page tool) but the resource and its contents are concrete enough that an agent knows what comes back. It does not contrast itself with sibling tools like get_offers or get_vendor, which keeps it from 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?

One explicit usage rule is given: 'Call with no slug to list the pages,' which covers the no-argument mode. However, there is no guidance on when to use this page-level tool instead of the sibling offer/vendor/pack tools, so an agent must infer the boundary from names alone.

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