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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuine behavioral value beyond that: it discloses the return shape (latest AND previous DONE result, grouped per strategy, plus queued entries), which tells the agent this returns historical comparison data, not just a single current score. Missing are edge behaviors like what happens when no results exist yet.

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?

A single front-loaded sentence tagged with [read], with zero filler. The key scoping information (DONE vs queued, per strategy, website identifier) lands immediately.

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 simple two-parameter read tool with full annotation coverage and no output schema, the description supplies the essential shape of the response and the identifier alternation. Only the no-identifier case is unspecified, which is a minor but real omission given both params default to null.

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 parameter burden. It does clarify that a website is selected by `seliee_website_id` OR `seliee_website_uuid` (mutually alternative identifiers), which is real added value over a bare anyOf. But with both parameters optional and defaulting to null, the description never states what happens when neither is supplied (all websites?), leaving a meaningful gap.

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 description names a specific resource (PageSpeed results) and scope: latest and previous DONE results per strategy, plus queued items. That's far more specific than the title, and it's clearly a read operation distinct from run_pagespeed. It stops short of explicitly naming the sibling it pairs with (run_pagespeed to kick off a test), so 4 rather than 5.

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 implied rather than stated: mentioning 'DONE' results and 'anything still queued' hints that this is a polling/status-read tool after run_pagespeed has been called. There is no explicit when-to-use vs alternatives (e.g., 'use run_pagespeed to start a new test') and no prerequisites stated.

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