Frontier: evidence-scored science breakthroughs

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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world tool, so the behavioral bar is low. The description adds that the content is explanatory/conceptual (methodology, rules, tiers), which is useful context, but it doesn't say anything about output shape or depth beyond that. A 3 reflects modest added value over the annotations.

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?

A single, front-loaded sentence that enumerates the subtopics covered. It is efficient and wastes no words, though the list-style phrasing is slightly dense.

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 zero-parameter, read-only explainer with no output schema or sibling differentiation, the description is adequate but leaves gaps: it doesn't say the call returns explanatory text versus a computed score, nor how it relates to the other breakthrough tools. It is minimally viable rather than fully complete.

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?

The tool takes zero parameters, so there are no parameter semantics to clarify and the baseline is 4. The description appropriately focuses on the resource instead of parameters.

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 resource (the Frontier Score method) and enumerates the topics it covers: three pillars, recency, integrity rule, tiers, confidence. It reads as documentation/explanation rather than fetching a score value, which is clear, though it does not distinguish itself from siblings like get_breakthrough or list_fields.

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 indication of when an agent should call this versus related siblings (get_breakthrough, search_breakthroughs). Usage is only implied by the resource name; there is no when-to-use or when-not-to-use 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 readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, so the safety profile is covered. Beyond that, the description discloses substantive behavior no structured field provides: it guarantees 'Everything Frontier holds on one entry' and enumerates the payload composition (pillar drivers, recency/confidence, per-figure sources). It stops short of documenting failure behavior for unknown or ambiguous IDs, which keeps it out of 5 territory.

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?

One long but well-structured sentence, front-loaded with the completeness guarantee ('Everything Frontier holds on one entry') followed by the payload inventory and the accepted ID forms. Each clause carries distinct information; the only minor cost is the sentence's length.

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, the description carries the return-value burden and does so thoroughly — it enumerates the summary, significance, authors/institutions, full score breakdown with drivers, recency/confidence, and sources. ID formats are covered. What is missing is edge-case context (behavior on unknown/ambiguous IDs and its relationship to explain_frontier_score), so it is not fully complete.

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 id parameter's meaning (OpenAlex work id, entry slug, or entry URL) is already in the schema. The description restates the same three formats and adds only one concrete example ('W7214802080'), a marginal value-add over the schema. Baseline 3 for a high-coverage single-parameter schema 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?

The description states a specific verb and resource — retrieve the complete record for a single entry — and enumerates exactly what that record contains (summary, why-it-matters, authors, score breakdown, sources). The scoping phrase 'one entry' implicitly separates it from the list-oriented siblings latest_breakthroughs and search_breakthroughs, though neither sibling is named explicitly, 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?

Use is only implied: 'one entry' plus the accepted ID forms suggest this is the tool for fetching details of a known entry, as opposed to searching or listing. There is no explicit when-to-use/when-not statement and no pointer to explain_frontier_score or search_breakthroughs as alternatives, so the agent must infer the 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 already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds real behavior beyond that: the index adds a few top-journal papers every day and results are newest first. It omits return shape and any paging/limit interaction, but the freshness and ordering context 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?

A single tightly packed sentence that front-loads the operation ('What Frontier added most recently') and appends the scoping details. No filler or redundancy.

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 read-only listing tool with no output schema, the description supplies enough to call it correctly: recency window, ordering, and optional field filter. Missing only edge-case behavior (e.g., empty window) and the limit's effect on ordering.

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 days, field, and limit are already documented with ranges and defaults. The description confirms recency semantics ('last N days') and that field is optional ('optionally within one field'), which mostly restates the schema rather than adding new meaning.

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 resource and scope: entries added in the last N days, newest first, optionally filtered to one field. This is clearly a recency-based listing distinct from get_breakthrough and search_breakthroughs, though it never names those siblings explicitly to route the agent.

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 implied rather than stated: the description makes clear this is for pulling recent additions, and 'see list_fields' hints at the field filter. It does not say when to prefer this over search_breakthroughs or when a time-window listing is the wrong choice, leaving the routing to inference.

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=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds return-content context (entry counts and median score), but no pagination, ordering, or cardinality behavior. With annotations carrying the load, a 3 is appropriate.

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?

A single front-loaded sentence that states the resource and both returned metrics with zero filler. Every clause earns its place.

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 no-parameter, no-output-schema listing tool whose annotations fully cover the safety profile, the description tells the agent enough to invoke it. Minor gap: no hint about how many fields or whether results are ordered.

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?

The tool takes zero parameters and the schema is empty, so there is nothing for the description to document. Baseline 4 applies; the description correctly makes no parameter claims.

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 resource ('research fields Frontier covers') and what the tool returns ('how many entries each holds and its median Frontier Score'). Clear verbless but resource-specific; however it does not distinguish itself from siblings like search_breakthroughs, 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?

Usage is implied: this is a directory-listing tool for enumerating fields. There is no explicit when-to-use guidance, no statement of when to prefer it over explain_frontier_score or search_breakthroughs, and no exclusions.

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 the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower. The description adds real behavioral context beyond that: matching scope, default ranking by Frontier Score vs newest paper, and the exact payload returned (summary, score, Frontier URL, DOI). No pagination or rate-limit detail, but nothing contradicts annotations.

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?

Three dense sentences, each carrying distinct information: what to search, how matching/ranking works, and what comes back plus the empty-query escape hatch. Front-loaded with the core action and free of filler, though the sentences are long and could be split for scanning.

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, the description correctly absorbs the burden of describing return contents (summary, score, Frontier URL, DOI) and ranking behavior, and it cross-references list_fields for the field enum. Missing only minor operational detail such as result-count/pagination behavior.

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 already 100%, so baseline is 3. The description goes further by explaining what 'query' actually matches against (titles, plain-language summaries, authors, topics) and that field limiting is optional and can be combined with an empty query to browse — meaning the schema does not carry on its own.

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?

Specific verb (search) and a precisely scoped resource ('Frontier's evidence-scored index of new research from the top scientific journals'), plus what the match covers and how results are ranked/sorted. It distinguishes itself implicitly from get_breakthrough and latest_breakthroughs, but never names a sibling, so sibling differentiation is left to inference.

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?

'Leave the query empty to browse a field' is a useful usage note, and the field/sort interaction is implied. However there is no guidance on when to prefer this over latest_breakthroughs or get_breakthrough, and no exclusions or prerequisites stated.

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