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

With no annotations, the description carries the entire burden and does so: it discloses async polling semantics, per-site state machine, null-vs-zero semantics, billing/refund behavior including refund reasons and underReview, that reads settle due refunds, a 30-day expiry, and a 1000/day per-IP read cap returning 429 READ_RATE_LIMITED. It also states no quota is consumed and that possession of comparisonId is the only access requirement.

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 first sentence is well front-loaded, but the body is three dense run-on paragraphs mixing return-value semantics, presentation instructions, and billing detail with no headings or bullets. Given there is no output schema much of this content earns its place, yet the size and density are heavier than needed for a one-parameter read.

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?

No output schema exists, so the description must explain return values, and it does thoroughly: per-site states, summary median/max/own/gap, recommendation thresholds and null reasons, failure codes, billing breakdown, and refund statuses. An agent can interpret and present the response without guessing.

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 single parameter is fully described in the schema (22-character ID from the creation call), so the baseline is high. The description adds the meaningful security/access fact that whoever holds the comparisonId can read it, which explains why the ID is sufficient, but adds no format or validity guidance beyond the schema.

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?

Opens with a specific verb+resource ('Read a comparison of editorial velocities') and immediately identifies the creator sibling ('Returns the comparison started by POST /api/v1/tools/editorial-velocity/comparisons'), which cleanly separates it from create_editorial_velocity_comparison. It also distinguishes itself from get_editorial_velocity by explaining that analysisId links to the per-site analysis.

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?

Explicitly says to call again every 15 seconds while status is pending or running, names the failure path (status failed with SERP_FAILED/INTERNAL), and routes the agent to the sibling get_editorial_velocity for full single-site analysis. There is no ambiguity about when to use this versus alternatives.

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