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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuine value beyond that: 'no auth required', the data source (Figshare.com), the CC-licensed nature of the content, the publication-date sort behavior, and the exact return fields. This contextualizes what the agent can expect from the operation without contradicting any annotation.

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 description is four sentences and every sentence earns its place: the search scope and examples come first, then the filter modes and sort behavior, then the return fields and downstream tool linkage, then the data/source/auth context. Information is front-loaded and nothing is redundant with what the schema already documents.

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 read-only, idempotent search tool with an output schema present and annotations covering the safety profile, this description is complete. It tells the agent what repository is searched, what filters are available, how results are sorted, what fields come back, which sibling to use for follow-up detail, and that no authentication is required. Nothing an agent needs to decide whether and how to invoke it is missing.

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% — all six parameters (doi, page, query, item_type, page_size, order_direction) have descriptions in the schema itself, so the baseline of 3 applies. The description adds marginal value by restating the filter modes ('free-text query, exact DOI, or research output type') and giving examples like 'soil moisture' and 'gene expression', but it does not add parameter-level meaning that the schema lacks.

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 states a specific verb and resource — 'Search Figshare's open research repository' — and enumerates exactly what is searchable (datasets, figures, papers, preprints, media, etc.) with concrete query examples. It clearly distinguishes itself from the sibling figshare.articles.details by noting the returned id is 'for use with figshare.article_details', so an agent can tell this search tool apart from its companion detail tool without inspecting either schema.

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 description makes the tool's scope clear: it is for searching an open research repository, with filter modes (free-text, DOI, item type) and a default sort by publication date. It implicitly routes to the sibling detail tool by prescribing where the returned id should be used. There are no explicit when-not-to-use exclusions against the many other academic search siblings (crossref.works.search, zenodo.records.search), but the Figshare-specific context plus the 'no auth required' note give an agent adequate guidance.

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