webmaster_apply_recrawl

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

Annotations already declare idempotentHint=true, readOnlyHint=false and openWorldHint=true. The description adds real value beyond them: the single-submission contract and the explicit retry rule for uncertain POSTs (reconcile instead of retransmit), which is exactly the behavioral nuance an agent needs on a networked write. It omits any mention of auth/approval prerequisites, keeping it short of a 5.

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 short sentences, front-loaded with the core action and followed by the retry caveat; no filler. It is efficient, though the extreme brevity is arguably under-specification rather than true conciseness.

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 values need not be described. However, this is an open-world mutation taking four required inputs, and the description never explains the approval flow that produces approval_id or the role of host_id and idempotency_key. It covers the retry hazard but leaves the invocation prerequisites incomplete.

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% and all four parameters are required, so the description must carry the meaning. It only obliquely explains url ('accepted URL') and approval_id ('accepted'), and says nothing about host_id or idempotency_key. Three of the four parameters remain unexplained anywhere.

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?

The verb 'Submit' and the object 'one accepted URL' convey that this applies a previously accepted recrawl request, but the word 'recrawl' never appears in the description and 'accepted' is left undefined. An agent must infer from the tool name and the approval_id parameter that this is the apply step of a prepare/apply recrawl flow. It is not clearly distinguished from siblings like webmaster_prepare_recrawl or webmaster_reconcile_action.

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?

'Submit ... exactly once' and 'Uncertain POSTs are reconciled without retransmission' give implicit retry guidance: on an ambiguous outcome, reconcile rather than re-POST. That is useful inferred usage, but the description never names webmaster_reconcile_action, nor does it state the prerequisite that the URL must first pass a prepare/approval step.

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