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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuine behavioral rules beyond them: a 75% coverage gate, a 60% hack cap, and too-close-to-call handling below 3 points. These disclose that results may be gated or flagged, though the description doesn't state what the agent sees when a gate trips.

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?

Two tightly packed sentences with the scope and constraints front-loaded and no filler. It is slightly jargon-dense ('60% hack cap') in a way that assumes familiarity, but nothing is wasted.

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?

An output schema exists, so return shape need not be explained, and the annotations carry the safety profile. The description covers scope, weighting, and the rubric gates, leaving only the practical consequence of a failed gate unstated — a minor gap for a read-only comparison tool with rich structured fields.

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%, so both the weights map (0-10, default 5, keyed by get_platform criteria) and the platforms array are already fully documented in the schema. The description only restates 'optional criterion weights' and the 2-6 count, adding no syntax or meaning beyond the structured fields.

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?

States a specific verb and resource ('Compare platforms') plus scope constraints ('2-6 platforms in one category') that separate it from single-platform siblings like get_platform. It does not explicitly name or route against alternatives such as get_verdict, so it falls just short of full sibling differentiation.

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 2-6 same-category constraint and optional weights imply when the tool is appropriate, but there is no explicit 'use this when...' statement and no named alternative for cases like single-platform lookups or verdicts. Usage is inferable but not directed.

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