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

With no annotations, the description carries the full load and does substantial work: it discloses the price ($0.05 USDC on Solana per grade), that one payment buys exactly one deterministic grade, that grading is table-entry-cited rather than free-form, and that there is deliberately no composite score. It stops short of stating what happens on an invalid nonce, mismatched canary, or failed payment, which is the remaining gap for a paid mutation-shaped call.

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 sentences, front-loaded with price then purpose, and the scope disclaimer is placed last where it belongs. It is a dense semicolon chain and a touch repetitive ('The grade grades'), but very little could be cut without losing meaning.

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 describe the return payload — and it does: per-probe grade, cited expectation-table entry, behavioural outcome, binding-strength wording, canary status, factors, and explicitly no composite score. Given the nested probes object and the paid-call complexity, the only missing piece is error/failure semantics.

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 each of the 8 parameters has its own description, so the baseline is 3. The description reinforces the five probe ids and the canary notion ('the canary status', 'the canary echo') with the outcome semantics (RUNNABLE / PARTIAL / NOT RUNNABLE), but adds no syntax or format detail beyond the schema, and says nothing about the optional variant, declared_scope, or claimed_expectations.

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+resource with full scope: it grades one submitted probe transcript across five named probes (persistence truth, scope coherence, replay duplication, repeatable read, feature liveness) against the declared family's published expectation table. An agent can tell this apart from probe_grade_criteria (rubric) and probe_grade_precheck without opening any schema.

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?

Usage is only implied: it grades 'the one probe transcript you submit' from a challenge run, which implies a prior script run and issued nonce, but it never names the sibling to call first (probe_grade_precheck / probe_grade_criteria). It does give one useful exclusion — 'not a certification of your production store' — but no positive when-to-use instruction.

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