UK Data: Research papers

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

No annotations are supplied, so the description carries the full disclosure burden. It usefully reveals that results include abstracts and PDF links and that each call costs 1 credit, but says nothing about ordering, pagination, result caps, or failure behavior for malformed queries.

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?

Two compact sentences: the capability and its return content come first, with the credit cost appended in parentheses. Nothing is redundant or buried.

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 no output schema and no annotations, the description covers what it does, what it returns, and its cost. The remaining gaps (query syntax, pagination/limit semantics) are modest rather than blocking.

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 100%, so both parameters (query, limit with range 1-50) are already documented in structured form. The description adds no query syntax hints (e.g., field prefixes, boolean operators, category filters) that would go beyond the schema, so baseline 3 applies.

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?

"Search arXiv preprints" gives a specific verb and resource, and naming arXiv distinguishes it from pubmed_search and doi_lookup. It also states what comes back (abstracts, PDF links), though it never contrasts itself with papers_search, which may overlap.

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 only implied via the arXiv domain name; there is no explicit when-to-use or when-not-to-use guidance and no mention of papers_search as the alternative for cross-source or non-arXiv queries. An agent can infer the source scoping but must reason about sibling overlap itself.

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

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

With no annotations, the description carries the full burden and discloses only the 1-credit cost. It does not state read-only behavior, what happens for an unknown or malformed DOI, whether the call fails or returns an empty payload, or any rate limits.

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?

Two short fragments with no wasted words, but the brevity comes at the cost of under-specification rather than disciplined concision. The cost note is front-loaded well but sits alongside a bare noun phrase rather than a complete statement of action.

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 tool with no annotations and no output schema, the description should say what metadata is returned (title, authors, citation counts?) and how failures surface. Neither is covered, so an agent knows the input but not what it will get back or how errors behave.

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 the single 'doi' parameter is technically documented, but the schema text is only 'string, required'. The description adds that the value must be a DOI resolvable via Crossref, which is a marginal but real clarification beyond the schema.

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 fragment 'Metadata for a DOI from Crossref' identifies the resource and data source, but relies on the tool name for the verb 'lookup'. It does not explicitly contrast itself with siblings like papers_search or arxiv_search, which an agent might reasonably pick for a similar metadata-fetching task.

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?

No when-to-use guidance is given: nothing says to call this only when a DOI is already known, or to use one of the search siblings when only a title/author is available. The credit cost note hints at frugality but is not usage direction.

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

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

With no annotations, the description carries the full burden. It does disclose two things structured data does not: the credit cost (1 credit) and the shape of the returned fields, which is meaningful for a paid call. It says nothing about result ordering, pagination/total counts, rate limits, or error behavior, so the mutation/consumption profile is only partially covered.

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?

Two compact clauses, front-loaded with the action and resource, then return fields, then cost. No filler or restatement of the name.

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 4-parameter read tool with no output schema and no annotations, enumerating the returned fields plus the credit cost covers most of what an agent needs to decide and call. The remaining gap is behavioral detail around result limits and source-specific differences, which the description leaves entirely implicit.

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 100%, so all four parameters are already documented, making 3 the baseline. The description adds one genuinely new fact not in the schema: that source defaults to OpenAlex. It adds nothing about limit's interaction with totals or the year-range semantics.

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+resource ("Search scholarly papers") and enumerates what comes back (authors, venue, year, DOI, citations, open-access link), plus the two underlying sources. It does not name or contrast with any sibling (arxiv_search, pubmed_search, doi_lookup), so the agent must infer the boundary itself.

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 only usage signal is that OpenAlex is the default and Crossref is the alternative source. There is no statement of when to pick this over arxiv_search, pubmed_search, or doi_lookup, and no exclusions or prerequisites.

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

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

No annotations exist, so the description carries the full behavioral burden, and it only discloses a credit cost. It says nothing about return format, result ranking, pagination, rate limits, or whether queries support PubMed field tags/MeSH syntax.

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?

Two short fragments, zero filler, and the core purpose is front-loaded before the cost note. The terseness borders on under-specification, but no sentence is wasted.

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 annotations and no output schema, the description should explain what results look like and how to shape queries for a domain-specific literature index. Instead it provides only a one-line scope plus cost, leaving the agent to guess at result shape and query capabilities.

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 100%, so the two parameters (query, limit) are already documented, establishing the baseline of 3. The description adds no meaning beyond the schema — notably nothing about PubMed query syntax that would materially help an agent construct 'query'.

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 and resource ('Search PubMed biomedical literature'), which is clearer than a bare name restatement. It implicitly scopes the tool to biomedical literature versus the arXiv/preprint focus of arxiv_search, but never names or contrasts the siblings directly.

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?

There is no explicit when-to-use or when-not-to-use guidance and no mention of when to prefer this over papers_search or doi_lookup. The agent must infer selection from the word 'PubMed' alone.

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