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

Annotations already declare the write/destructive/open-world profile, and the description adds genuinely non-redundant behavior: the operation is asynchronous and queue-only, capped at 50 websites, with strategies defaulting to both. It does not explain the consequence of the destructiveHint=true flag (e.g. whether re-running overwrites prior measurements), which is the main remaining gap.

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, both dense and front-loaded: the operation and its limits come first, the polling follow-up second. Nothing is padded and the bracketed [write, queued] tag immediately signals the mode.

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 3-param queued mutation with annotations and no output schema, this covers what an agent needs: what gets queued, for how many, with which strategies, and how to observe completion. The missing piece is what the immediate response contains (queued job ids? row counts?) and whether duplicate submissions are de-duplicated.

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 0%, so the description must carry the load, and it does: it explains that websites are addressed by ids and/or uuids (implying at least one is needed), and it documents the strategy parameter's allowed values (MOBILE/DESKTOP) and its default. It never names seliee_pagespeed_check_strategies directly and gives no format guidance for the uuid strings.

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 ("Queue PageSpeed measurements") plus scope limits (up to 50 websites, MOBILE/DESKTOP, default both). It explicitly distinguishes itself from the retrieval sibling by saying it only queues and that get_pagespeed_summary is the read path.

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?

Names the follow-up tool and the exact condition to poll it ("until rows go PENDING -> DONE"), which is the key routing decision an agent faces here. It stops short of stating when not to use it (e.g. re-running against already-DONE rows), so it is clear but not fully exclusionary.

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