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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so safety is covered structurally. The description adds that results are paginated and mentions the optional similarity_threshold, but omits fuzzy-match behavior details (how threshold affects inclusive vs. near matches) that would matter for an image-hash query.

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?

Compact: one dense sentence covering inputs and outputs plus a short benefit statement. Front-loaded with the core purpose, though the parenthetical enum list is somewhat redundant with the schema and makes the sentence heavy.

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 the URL/title/time recap is unnecessary padding, and the description could instead spend those words on the hash_value format and hash-type semantics. Pagination and the optional threshold are covered, but sibling routing and fuzzy-match semantics are missing for a 5-parameter search tool.

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%, so the description must carry the load. It enumerates the hash_type values and marks similarity_threshold as optional, but those enum values already appear in the schema, and it never explains what each hash algorithm means, the expected format of hash_value, or the units of page/limit beyond the word 'paginated'.

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 ('List scans') and resource (screenshot perceptual hash), making it clearly a hash-lookup search rather than a generic scan search. It does not, however, differentiate itself from close siblings like search_similar_screenshots or search_by_favicon, leaving some ambiguity in the 'image similarity' family.

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?

The closing line 'Useful for finding pages that look the same' implies the use case, but there is no explicit when-to-use rule or guidance on when to prefer search_similar_screenshots or other similarity searches. Usage is inferable rather than stated.

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