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

Goes well beyond the annotations (destructive/openWorld/not-readOnly) by disclosing the cost model (completed checks cost 1 credit even when the target is broken, worker failures cost zero), budget-stop behavior, minimum interval, confirm gating, signed webhook transitions, MCP baseline/schema-drift semantics, and best-effort scheduling. This is exactly the operational context annotations can't carry.

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?

Front-loads the core definition, then packs differentiated facts into short, declarative sentences with no filler. Every line adds a distinct operational fact (cost, gating, idempotency, webhook, MCP drift, scheduling caveat).

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 9-param, mutation-style scheduling tool with an output schema available, the description covers prerequisites, cost, safety semantics, idempotency, and scheduling caveats. Return format is correctly omitted since an output schema exists, and nothing needed to invoke it correctly is missing.

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?

With 0% schema description coverage across 9 params, the description carries the burden and does so for nearly every meaningful field: api_key (utility account key), max_coins (spending cap), request_key (idempotent retries), confirm (must be true to start), interval_sec (min 300s, default hourly), webhook_url (public HTTPS, signed, save secret), and kind (HTTP vs MCP). Only name and url are left to inference, which is trivial here.

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 ('Watch a public HTTP endpoint or MCP server on a recurring schedule') and scopes it as recurring and private. This clearly separates it from the one-shot diagnose_http / diagnose_mcp siblings without naming them, so an agent can route correctly.

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 concrete prerequisites and usage rules: requires a utility account key, an explicit max_coins cap, owner consent, 'nothing starts unless confirm=true', and 'save/reuse request_key on uncertain retries'. It never explicitly frames when to choose this over the one-off diagnostic tools, but the recurring-watch framing makes the context clear.

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