cern-inspire-mcp-server

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

Beyond the annotations (readOnly/openWorld/idempotent), the description discloses the 10,000-reachable-match cap and that entries are INSPIRE's verbatim text with long author lists abbreviated as 'Name and others'. It does not detail error behavior or the response envelope, but it adds real operational context.

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?

Front-loads what is exported and the formats before moving to selection syntax and limits; every sentence carries information. The inline example strings make it dense, but nothing is wasted or redundant.

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 return-value shape need not be explained, and the description still covers formats, selection syntax, pagination limits, and data quirks. Nothing an agent needs to call this correctly 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%, so 3 is the baseline, but the description contributes extra query-syntax examples ('t higgs and topcite 500+', 'a Edward.Witten.1', 'refersto:recid:451647') and the invalid-clause rule for empty fields like 'a:'. This goes beyond what the schema documents.

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 (export INSPIRE citation entries for query-selected papers) and the output formats (BibTeX, LaTeX \bibitem, EU/US style). It is clearly distinct from siblings like cern_inspire_search_literature, which returns records rather than paste-ready citations.

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?

Gives concrete selection modes (named paper via recid/arxiv/doi, or a topic/author/citing set via any cern_inspire_search_literature query) and notes the 50-per-page and 10,000-match ceilings. It does not explicitly say when to prefer search_literature or get_paper instead, so routing past the sibling is left partly implicit.

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?

Annotations already declare readOnlyHint/idempotentHint, so the lowest bar is met. The description adds real behavioral caveats beyond them: combining year_from/year_to/exclude_self_citations drops the citations-per-year figure because INSPIRE cannot narrow it that way, and empty field clauses like 'a:' are invalid rather than silently ignored.

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?

Front-loads the computed metrics before the input modes, which is the right order. It is a single dense paragraph with some redundancy against the schema's own parameter descriptions, but every sentence carries usable content and nothing is padding.

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 an output schema present, return values need not be re-explained, and the description still covers the output dimensions, the two mutually exclusive input paths, name-resolution prerequisites, and the filter-combination caveat. Nothing an agent needs to call this correctly 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%, so the schema already documents every parameter and the baseline is 3. The description still adds interaction meaning the schema states only per-parameter: the 'exactly one of' constraint across author/query, and that document-type and subject filters narrow every reported figure.

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?

Opens with a specific verb and resource ('Compute INSPIRE-HEP's citation summary') and enumerates exactly what is produced (h-index, totals, averages, per-bucket counts, per-year citations) for two input modes. An agent can distinguish this from cern_inspire_export_citations (raw citation export) without opening any 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?

States the selection rule precisely ('Pass exactly one of author ... or query') and gives a prerequisite workflow ('resolve a name with cern_inspire_search_authors first'). It does not explicitly name export_citations or say when a summary is preferable to exporting citations, so sibling routing is only partially covered.

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?

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds real operational context beyond that: large collaboration papers can list thousands of authors, max_authors caps the list, and authorCount always exposes the true total.

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 verb and identifier forms are front-loaded, and the long field enumeration is dense but earns its place by telling the agent what the record contains. The pagination note is useful rather than filler. Slightly long overall but not padded.

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, yet the description still sketches the payload (authors, abstract, identifiers, HEPData tables, ready-made queries) and the key pagination mechanics. Nothing needed to invoke it correctly 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 description coverage is 100%, so the baseline is 3. The description restates the max_authors/authorCount relationship already documented in the schema and adds no format or syntax detail the schema lacks, so it does not exceed baseline.

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?

Opens with a specific verb+resource ("Fetch one paper's full INSPIRE-HEP record") and immediately names the three identifier forms accepted. This clearly separates it from discovery-oriented siblings like cern_inspire_search_literature.

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 identifier-based framing makes the usage context clear: call this when you already hold a recid/arXiv ID/DOI. It stops short of explicitly contrasting with search_literature or noting what to do when you only have a title, so no exclusion is stated.

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?

Annotations already declare readOnly/idempotent/not-open-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: 'Static content with no upstream call' (no network, always succeeds) and the fact that it documents the 10,000-result window and how malformed queries behave. It stops short of describing the response shape, but that is minor given the output schema exists.

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?

Front-loaded with the core purpose, then the enumerated topics, then the usage trigger. The single long sentence listing topics is dense but every clause maps to an actual enum value, so little is wasted; it could be marginally tighter.

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 one-enum static reference tool with an output schema already present, the description covers everything an agent needs: what each topic contains, that it is offline/static, and when to reach for it. No return-value explanation is required.

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% and the single enum parameter is fully documented in the schema, so the baseline is 3. The description restates the enum categories (search syntax, identifier forms, etc.) with marginally more detail than the schema, but adds no format or syntax guidance beyond it.

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: 'Decode the vocabulary the other cern_inspire tools take,' and then enumerates exactly which vocabularies (search syntax, identifier forms, document_types, subjects, citation buckets, HEPData). This clearly distinguishes it from the search/get siblings, which consume that vocabulary rather than explain it.

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?

Gives explicit trigger conditions: 'use it to build a query or to recover from an empty or unexpectedly broad result.' It also clarifies the relationship to the alternatives ('the other cern_inspire tools take'), so an agent knows this is the pre-query/recovery helper rather than a retrieval tool.

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?

Annotations already cover safety (readOnly, idempotent, openWorld), so the description's job is to add match behavior — and it does: names return ranked candidates with ambiguity risk, identifiers match exactly. It stops short of describing pagination or result ordering beyond ranking, but the added ambiguity warning is genuinely useful.

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?

Front-loaded with the purpose, then value, then usage guidance; every sentence earns its place. It is dense and slightly long, but not padded — no restatement of the title or 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?

With an output schema present, the description needn't enumerate returns, yet it still previews the profile shape and the literatureQuery handoff. Together with the routing advice, an agent has everything needed to call it correctly.

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% and the schema already lists accepted identifier formats, so baseline is 3. The description adds match semantics per query type (ranked candidate list for names vs exact for identifiers) that the schema does not convey, pushing it slightly above baseline.

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 (find physicist profiles in INSPIRE-HEP) and enumerates the five accepted lookup keys. It is clearly distinguishable from siblings like cern_inspire_search_literature and cern_inspire_get_citation_summary, which it names.

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?

Explicitly routes the agent: confirm the person via positions/categories before passing a bai or recid to cern_inspire_get_citation_summary, and notes the literatureQuery feeds cern_inspire_search_literature. It also warns that a bare surname can match tens of thousands of profiles and that a less-cited namesake can rank first, which is real when-not-to-trust guidance.

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?

Annotations already declare readOnly, idempotent, and openWorld, so the safety profile is covered. The description adds real behavioral value beyond that: the exact record contents (accelerator, institutions, subgroups, lifecycle dates, paper count) and the chaining affordance via literatureQuery, which an agent could not infer from annotations alone.

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 sentences, front-loaded with the searchable resource and examples before the record-shape detail. Dense but every clause carries information; slightly long, though 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?

An output schema exists, so return values need not be re-explained, yet the description's enumeration of record fields is still useful for judging downstream chaining to the literature tools. Combined with annotations covering safety, nothing essential for correct invocation 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%, and the schema description already spells out the accepted query forms (name, legacy name like CERN-LHC-CMS, digits-only recid). The description restates these acceptable inputs but adds no format details or edge-case semantics beyond the schema, so the 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?

States a specific verb ('Find') and resource ('experiments, collaborations, and facilities in INSPIRE-HEP') with concrete examples (ATLAS, CMS, DUNE, Belle II). The scope is clearly narrower than search_literature or search_authors, so an agent can select it without opening any 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?

Gives clear context on what can be searched (name, accelerator, INSPIRE legacy name, recid) and explicitly routes downstream work to cern_inspire_search_literature or cern_inspire_get_citation_summary via the literatureQuery field. It stops short of stating when to prefer this over search_authors or search_hepdata, so it is not a full when/when-not statement.

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?

Goes well beyond the read-only/idempotent annotations: it enumerates the payload fields an agent will get back (recids, collaborations, keywords, recordDoi, latest version, table count, hepdataUrl), states explicitly that the table values themselves are NOT returned, and discloses the 10,000-result reachability cap. These are exactly the traits an agent needs to plan a call and a follow-up.

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 purpose and the key routing hint are front-loaded, and the payload enumeration is information-dense rather than padding. The first sentence is long and clause-heavy, but every clause carries a distinct fact; only the trailing result-cap sentence is a slight add-on.

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?

The definition covers purpose, selection condition, payload contents, the explicit non-return of data values, and the hard result ceiling, with downstream routing to cern_inspire_get_paper. For a 4-parameter search tool with a full output schema, nothing an agent needs in order to call it correctly 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%, so the baseline is 3, but the description adds meaning by naming the physics facets the query field operates over (process, observable, energy, collaboration) and by flagging that the result cap applies to the query, which reinforces the page/size limits. It does not add syntax beyond the schema's examples, so it is a modest lift above baseline.

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 ('Find HEPData measurement records') plus the searchable dimensions (process, observable, energy, collaboration) and the data source (INSPIRE-HEP's index of HEPData submissions). This clearly distinguishes it from sibling paper-oriented tools like cern_inspire_search_literature and cern_inspire_get_paper.

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?

'when the paper is unknown' gives an explicit selection condition against the sibling tool that finds papers, and 'pass to cern_inspire_get_paper' describes the onward step. It stops short of an explicit when-not clause (e.g. 'if you already have the recid or DOI, use X instead'), so it is clear context rather than full routing.

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?

Annotations only declare readOnly/openWorld/idempotent; the description adds substantive behavior beyond that: the 10,000-result reachability ceiling, that empty recognized field clauses are invalid while other malformed syntax is passed through unvalidated, and how malformed syntax can widen or empty the match. That is exactly the extra context annotations cannot carry.

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?

Front-loaded with purpose, then returns, then routing, then caveats; every sentence carries information. It is dense and slightly long, but no sentence is filler or redundant with the title.

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 8 parameters, an output schema, and read-only annotations, the description still supplies the operational caveats an agent needs (result ceiling, invalid clause syntax, malformed-query symptoms and where to look up syntax) plus the follow-up tool paths.

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% and the schema already documents operators, page/size limits, sort enum, and the year/document_type/subject filters in detail. The description's query-syntax and filtering mentions largely restate the schema; the 10,000 limit also appears in the page parameter description. Baseline 3 is appropriate.

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 INSPIRE-HEP papers), names the query modes (INSPIRE syntax or free text) and the filter/sort dimensions, and explicitly routes to siblings (cern_inspire_get_paper, cern_inspire_export_citations) rather than leaving the agent to guess.

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?

Gives explicit next-step routing ('pass a recid to ... get_paper for the full record or to ... export_citations ("recid:N") for BibTeX') plus a diagnostic path when results look wrong (check cern_inspire_list_reference topic search_syntax). Conditions for each alternative are stated, not implied.

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