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

Annotations already state readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds behavior beyond that: results are ordered newest first, matching is on a substring of the name, and each result carries its address, paste-ready Markdown, the posts displaying it, and their alt text — valuable since there is no output schema.

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 pre-upload warning is well placed and earns its space, but the opening sentence is awkwardly constructed ('On one site of the account, named in site'), and the trailing clause 'which says what the picture shows' is filler appended to an already clear statement about alt text.

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?

With no output schema and no annotations about results, the description does the right thing by enumerating the returned fields. It leaves out result volume/pagination expectations beyond the schema's page note, and — most importantly for a library with three overlapping search tools — it never clarifies how this differs from search_photos and search_docs.

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%, with defaults and an enum already documented, so the baseline applies. The description reinforces that matching uses 'part of their name' and that 'site' selects one site, but it never explains the 'kind' filter, which is the field that most needs disambiguation against search_photos and search_docs.

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 verb (find by part of the name) and resource (files already in the library) scoped to one site, and adds the ordering ('newest first'). It does not distinguish this from the close siblings search_photos and search_docs, even though the 'kind' enum suggests those overlap, so it falls short of a 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?

'Look here before you upload a picture again' gives one genuine pre-use rule, which is useful. However, there is no guidance on when to choose search_media over search_photos or search_docs, and no statement of when not to use it.

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