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

Despite having annotations, the description adds substantial behavioral context annotations cannot convey: 1-credit pricing with no signing surcharge, zero cost on worker/signing failure, a five-minute expiry that retries never renew, and idempotent request_key behavior returning the SAME bundle. It also inverts the naive assumption that a valid signature means success, and describes what the signature binds (URL, assertions, result, observation time, nonce).

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?

Purpose is front-loaded and every sentence carries real information about cost, signature semantics, failure behavior, or retry rules. It is dense to the point of near-overload and the pricing sentence restates one idea twice ('same 1-credit price, no signing surcharge'), but nothing is filler.

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 6-required-parameter, open-world, credit-consuming tool with an output schema, the description covers the hard parts an agent needs: prerequisites, cost, failure semantics, expiry, and retry idempotency. Remaining gaps are the allowed values/formats for kind, url, and expect, which neither the description nor the schema supplies.

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 0% across 7 parameters, so the description carries the full parameter burden. It meaningfully explains api_key (utility key), max_coins (must be explicit), evidence_nonce (random 16-128-char URL-safe value from the receiving principal) and request_key retry semantics, but leaves url, kind, and expect entirely unexplained.

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 (run) plus the resource (HTTP/MCP/assert diagnostic) and the distinctive artifact it produces (signed evidence for delegation), which naturally separates it from run_credit_diagnostic and diagnose_http. It never names a sibling explicitly, so an agent must infer the boundary from the 'signed'/'delegation' qualifier rather than being told.

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?

Gives clear operating rules: when retries are uncertain reuse request_key, when signing is inappropriate ('No generic signing of caller-provided claims'), and where to get verifier guidance (internet_utils_instructions). It stops short of an explicit 'use this instead of X when Y' comparison against the many sibling diagnostic and evidence tools.

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