Unfrozen Atlas of the Middle

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds two genuinely new facts: the source is public facts from unfreeze.us/about/, and it surfaces a paid booking link (commercially promotional content an agent should treat carefully). It says nothing about response size or format, so it stops short of a 4.

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 sentence, front-loaded with the primary subject (the person) before secondary content (grading, citation, booking). Efficient, though the four-item enumeration makes it slightly list-like rather than crisply prioritized.

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, static informational tool with no output schema, the description covers what an agent needs to decide to call it and what topics the response will cover. It does not indicate the shape or length of the returned content, which is the only meaningful remaining gap.

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 semantics to document and the baseline of 4 applies; the description correctly adds no parameter talk that would be noise.

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 enumerates the four content areas the tool returns (Gabriel Lopez bio, Atlas grading methodology, citation/license, booking link), which is specific enough to distinguish it from get_answer, get_study, search_studies, and list_loop_parts. It lacks an explicit verb ('returns'/'describes'), making it read as a topic list rather than a stated action, but the resource is unambiguous.

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 explicit when-to-use, when-not-to-use, or named alternative is given. Usage is only implied by the content enumeration — an agent can infer it should call this for author/grading/citation questions rather than for study data, but it must do that inference 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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. Beyond that, the description adds genuinely useful behavior: deterministic keyword matching with no AI, verbatim published answer text with graded sources and page URL, and an explicit no-guess fallback — all things the annotations cannot convey.

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 sentences, each earning its place: what it does, what it returns, and how it fails. The mechanism and scope are front-loaded before the return and fallback details.

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?

No output schema exists, yet the description fully specifies the return shape (answer text, graded sources, page URL) and the negative case (links instead of a guess). Combined with annotations covering safety, an agent has everything needed to call it and interpret the result.

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?

There is only one parameter and its schema description coverage is 100%, including a concrete example question, so baseline is 3. The description hints that phrasing matters via 'deterministic keyword matching' but adds no syntax, length or phrasing guidance beyond what the schema already provides.

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: it matches a question to the closest fact-checked Atlas answer page. It also distinguishes itself from retrieval-style siblings by naming the deterministic keyword-matching mechanism and the scoped domain (middle managers and change), so an agent can tell it apart from search_studies or get_study.

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?

Clearly framed as a lookup for a question that likely already has a published fact-checked answer, and it names the fallback path (Ask the Atlas and the Atlas links) when nothing fits. It stops short of explicitly contrasting with search_studies/get_study, so the sibling choice is left partly 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add context — and it does, enumerating the returned payload (citation, design, strength grade, Loop parts with verdicts, citing answer pages, unfreeze.us page). It omits not-found/invalid-slug behavior, which is the remaining gap.

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 sentence, front-loaded with the identifier and the tool's scope, with no filler. The trailing noun list of returned fields is long but every element is informative, though it reads densely and could have been split for scanability.

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 burden of describing returns and does so thoroughly, including nested content like Loop parts and citing answer pages. The main omission is behavior when the identifier is missing or unmatched, which matters given that neither parameter 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 coverage is 100%, so both parameters are already documented with formats, examples, and maxLength. The description adds only that the slug comes from search_studies and that either key is acceptable — useful but marginal over 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?

States a specific resource fetch (one Atlas study) and the two exact lookup keys (slug or DOI), and distinguishes itself from search_studies by naming it as the source of the slug. The agent can immediately tell this apart from search_studies/get_answer without opening a 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 phrase "from search_studies" establishes the discovery-then-fetch workflow, and "or its DOI" signals the two alternative lookup paths. It stops short of stating when-not to use it or what happens if neither identifier is supplied (0 required params), but the intended context is clear.

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 closed-world, so the safety profile is covered. The description adds real value beyond that by disclosing the shape of the payload, including the supporting/mixed/challenging evidence classification, which the annotations cannot convey.

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 sentence that names the resource first and then enumerates the returned fields in a compact parenthetical. Nothing is redundant and nothing is 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?

There is no output schema, so the description carries the burden of explaining return values, and it does so by listing all three fields including the evidence-count categories. It is essentially complete for a no-parameter read tool, with only minor gaps such as ordering or count semantics.

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 the baseline of 4 applies; there is nothing for the description to clarify about inputs, and it correctly spends no words on them.

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 parts of the Unfrozen Loop) and exactly what each record contains: a one-line description, study-support counts (supporting/mixed/challenging) and a page link. It is clearly distinct from get_study or search_studies, but it never contrasts itself with the closest sibling, about_unfrozen.

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 usage is only implied — an agent can infer this is the entry point for seeing the Loop's components — but there is no explicit when-to-use statement or guidance on when about_unfrozen would be the better call instead.

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, closed-world behavior, so the description only needs to add corpus context — which it does by stating the fixed 173-study corpus, the fields matched, and the full set of returned fields. Minor gaps: no mention of what happens when nothing matches or how ranking works.

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 action and scope, then matching behavior, then return contents, then filters. The nested parenthetical ('173 studies … each with a strength grade and … summary') is dense but carries relevant corpus context rather than filler.

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?

There is no output schema, and the description compensates by enumerating the returned fields (label, year, journal, design, grade, Loop parts, one-line summary, unfreeze.us page). Combined with the stated matching fields and filter options, 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%, so the baseline is 3; the description earns above that by explaining that query matches title, summary, setting, authors and journal — a semantic the schema's 'keywords or a short question' wording does not convey. It does not restate part/grade/limit details that the schema already covers.

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 the Atlas of the Middle') and pins the corpus scope (173 studies on middle managers and change) plus what is matched. An agent can immediately distinguish this from get_study (single record) and list_loop_parts (taxonomy) 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?

'Matches words in the title, summary, setting, authors and journal' and 'Filter by Loop part or grade' tell the agent how to use it effectively, and the query field example hints at keyword vs. question style. It never names get_study or get_answer as an alternative, so there is no explicit when-not guidance.

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