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

Beyond the annotations, the description discloses the return format (Markdown sections, each with its source page) and the query-less listing behavior, which is useful context. However, annotations declare destructiveHint=true and idempotentHint=false for what the description portrays as a pure read/search operation, and the description does nothing to reconcile that tension or mention any side effects, limits, or auth requirements.

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?

The core content is compact and front-loaded with the modes, but the opening sentence is a dangling fragment ("On one site of the account, named in site.") that repeats what the schema already says and reads awkwardly. The em-dash aside enumerating the docs contents is informative but adds length without changing agent behavior.

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 two-parameter, output-schema-less read tool, the description covers scope, both query modes, return format, and the companion resource for full pages — enough for an agent to call it correctly. The only gap is that it never addresses the conflicting destructive annotation, which an agent might reasonably want explained.

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 100%, so both parameters are already documented, including the prefix-matching rule for query. The description adds only the semantic that omitting query switches to a page-listing mode, and restates that site names the account's site, which the schema already implies via list_sites. Baseline 3 fits given the schema does the heavy lifting.

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 uses a specific verb and resource: it "Searches the PixelGlass docs" and clarifies the scope as the REST API docs of one site (both the site's and the admin's .json, keys, requests and answers). No sibling tool covers docs search, so confusion risk is low, but the opening fragment "On one site of the account, named in site" delays the actual statement of purpose until the second clause.

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?

It specifies two modes clearly: with a query it returns the best-matching sections, and "Without a query, it lists the pages." It also routes the agent to pixelglass://docs/{path} when a whole page is needed, which is a genuine alternative-behavior hint. There is no explicit guidance on when not to use it versus a sibling, but no sibling tool competes for this job.

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