ACEL Observatory

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

No annotations are provided, so the description must carry behavioral disclosure. It reveals that only 'published' entities are considered and that observed facts and readiness metadata are used, but it does not state whether the tool is read-only, what side effects it might have, what output to expect, or any permission requirements.

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 a single dense sentence with no filler or repetition. It front-loads the core action and includes the key qualifiers (published, stated requirement, observed facts, readiness metadata) without wasting words.

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?

Given the absence of annotations, no output schema, and no parameter descriptions, the description leaves major gaps: what refs should contain, what the comparison output looks like, and whether any state changes occur. An agent would struggle to invoke this tool correctly without additional external knowledge.

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 0%, so the description must compensate. It hints at 'requirement' as the 'stated requirement' parameter but gives no explanation of what 'refs' contains (e.g., entity IDs, names, URLs) or how the requirement string should be formatted. This leaves the only required parameter, refs, semantically undefined.

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 ('Compare'), a specific resource ('published ACEL entities'), and a clear purpose ('against a stated requirement using observed facts and readiness metadata'). This clearly distinguishes it from sibling tools like get_entity, search_entities, and search_offerings, which perform different actions.

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 implies the usage context: comparing entities against a requirement when observed facts and readiness metadata are available. However, it does not explicitly state when to prefer this tool over alternatives like search_entities or get_entity, nor does it mention any 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?

With no annotations, the description carries the burden. It discloses that only published entities are returned and lists the returned components, which implies a read-only lookup. It does not mention not-found behavior, authorization requirements, or any side effects, but 'Return' conveys a non-destructive operation.

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 a single focused sentence with no unnecessary words. The action and result are front-loaded, making it easy to parse.

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-parameter lookup, the description is mostly sufficient and says what the response contains. However, it does not define what `ref` represents and omits edge-case behavior or response shape, which matters because there is no output schema.

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 single parameter `ref` has no schema description, and the description never mentions it. There is 0% schema description coverage and no compensation in prose; the parameter's role must be inferred entirely from its name.

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 clearly states the action ('Return') and the resource ('one published ACEL entity'), and specifies the included data: current facts, provenance, and trust state. It does not explicitly contrast with siblings like search_entities, but the wording does convey a single-entity lookup rather than discovery or comparison.

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 implies usage when you have a specific entity reference and need one entity's details, especially given the singular 'one' and 'published' wording. However, it gives no explicit guidance about when to use this tool instead of get_evidence, search_entities, compare_entities, or search_offerings.

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 are provided, so the description carries the burden of disclosing behavior. It does indicate a read-only 'Return' operation and specifies the content returned, which is useful. However, it does not disclose potential errors, permissions, freshness of facts, or any other behavioral caveats, leaving the agent with only a minimal behavioral picture.

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 a single well-structured sentence that leads with the action and object. It contains no filler or redundant phrasing, making it appropriately concise and easy to parse for an AI agent.

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 only one required parameter and no output schema, the description is reasonably complete in stating what the tool returns. However, it lacks essential detail about the 'ref' parameter and does not clarify the output structure or when to prefer this over get_entity, so it is only minimally viable.

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 input schema has one required parameter 'ref' with no description, and schema description coverage is 0%. The description does not explain what 'ref' should refer to, such as whether it is an ACEL identifier, a source reference, or some other key. Because there is no parameter documentation, the description needed to compensate but does not.

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 ('Return') and a specific resource ('source-linked evidence and current facts supporting an ACEL entity representation'), which makes the tool's purpose fairly clear. It distinguishes itself from search-oriented siblings, though the term 'ACEL entity representation' is somewhat jargon-heavy and could be clearer.

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 'supporting an ACEL entity representation' implies the tool is for retrieving evidence/facts behind an entity, but there is no explicit when-to-use guidance or mention of alternatives such as get_entity.js. Usage is implied rather than explained, so an agent must infer when this is the correct 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?

With no annotations, the description carries the behavioral disclosure burden. It does convey a read-only search and the return content ('trust state, canonical source and provenance'), but it omits caveats such as result ordering, pagination, or expected behavior on empty or ambiguous 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?

The description is two tight sentences: the first establishes the action and scope, the second states return fields. There is no filler, repetition, or unnecessary qualification.

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 search tool, the description is decent but not fully complete. No output schema or annotations exist, and the description does not explicitly say whether results are a list, how limit works, or any access or behavior caveats, leaving room for ambiguity during tool invocation.

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 0%, so the description must compensate. It adds useful meaning by framing q as a 'natural-language need' and naming category/locality as search dimensions, but it says nothing about the limit parameter or possible format constraints for category/locality.

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 uses a specific verb ('Search') and resource ('ACEL published entities'), and names the search facets ('natural-language need, category and locality'). This clearly separates it from siblings like get_entity and search_offerings by indicating what kind of lookup this is.

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 implies usage: use this when searching published entities by need, category, or locality. However, it provides no explicit when-not-to-use guidance or alternatives, so the agent must infer how this differs from get_entity or search_offerings.

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 provided, the description must carry the behavioral disclosure burden. It does state that results are 'observed' facts and enumerates fact types, which conveys the read-only, evidence-oriented nature of the tool. However, it does not disclose result shape, pagination, or any operational constraints beyond what the schema already provides.

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 a single sentence with no filler. The key verb, resource, and returned fact types are front-loaded, making it easy to scan. It earns its place despite being short.

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?

Given no annotations, no output schema, four parameters, and a closely related sibling tool, the description is too sparse to fully contextualize correct usage. It leaves q semantics, filtering behavior, result format, and sibling differentiation unaddressed.

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 0%, so the description should compensate by explaining what q, limit, category, and locality mean. It does not. Parameter names and basic types give some hints, but q's search semantics and category/locality filter behavior are left ambiguous.

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 uses a specific verb ('Search') and identifies the resource ('entities') plus the returned fact types: product, service, price, availability, and ordering-route facts. This clarifies that the tool surfaces offering-related observations, not just entity records. However, it does not explicitly distinguish itself from the 'search_entities' sibling, so it falls just short of full clarity.

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 guidance about when to use this tool versus alternatives like search_entities, get_entity, or get_evidence. The description implies a search-focused use case but never states exclusions or conditions that should route an agent to a sibling tool.

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