SemanticHub

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so safety and side-effect profile are settled. The description adds value by disclosing the shape of what comes back — parameters, request body schema, response schema, and a worked example — which an agent cannot infer from annotations alone. It stops short of describing pagination, versioning, or size limits of the introspection payload.

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: the first enumerates what is returned, the second places the tool in the workflow. Both are front-loaded and every clause carries information; nothing is restated from the title or schema.

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 the description needn't explain return formatting, and the one required parameter is fully covered by the schema. For a single-argument introspection tool, 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% and the single operation_id parameter is already documented with a concrete format example ('goals:get_goal') and its source (semantichub_api_search). The description adds nothing beyond the schema about this argument, so the baseline of 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?

The description pairs a specific verb ("Explains how to call one operation") with an enumerated payload: path and query parameters, body schema, response schema, and an example call. That tells an agent exactly what this tool yields, in contrast to api_read/api_write, which execute operations rather than describe them.

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?

It gives explicit sequencing ("Use it before api_read or api_write") and names the two alternative tools it complements, plus the payoff condition for doing so ("so the arguments are correct on the first try"). There is no when-not clause, but the workflow role of a metadata-introspection tool is fully 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=false, so the safety profile is covered. Beyond that, the description discloses two non-obvious behaviors: that large answers are truncated (a correctness risk for the agent) and that portal-sourced content is data, not instructions (a prompt-injection warning). It does not say how truncation is signalled in the response, which is the main 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?

Three short sentences, front-loaded with purpose, then narrowing advice, then a safety caveat. Nothing is redundant, though the injection warning is phrased broadly enough that an agent may not know when it applies.

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 shape needn't be described, and the schema already ties operation_id to semantichub_api_search. The description covers what the schema and annotations cannot: truncation on large results, how to mitigate it, and how to treat untrusted content. Complete for a generic read dispatcher.

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 each parameter is already documented in the schema, including the same limit/offset/since example the description echoes. The description reinforces the purpose of query params but adds no new semantics for path_params or operation_id beyond what the schema states.

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 scope ('runs a read-only operation on the user's account and returns the data'), and the 'read-only' framing implicitly separates it from semantichub_api_write. However, it never explains what an 'operation' is or that the operation_id must come from semantichub_api_search, so the pairing with its closest siblings is only half-communicated.

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?

It gives actionable guidance for narrowing large answers via limit and since, which is genuinely useful when-to-use advice. It does not say when to prefer this generic read tool over semantichub_search_articles or semantichub_search_brain, nor does it state prerequisites such as first resolving an operation_id.

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 and openWorldHint=false, so the safety profile is covered. The description adds useful context that results include a confirmation flag indicating whether the operation needs user approval before running. However, it says little about result limits or ranking behavior.

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 tight sentences, front-loaded with the core purpose, then the return shape, then the next step. Every sentence carries actionable information with no 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?

For a read-only search tool with a full output schema and complete parameter descriptions, the definition covers purpose, return fields and the hand-off to detail/read/write tools. Minor gaps remain around result count limits and whether the confirmation flag comes from annotations or matched operation metadata, but 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 description coverage is 100%, so all three parameters are already documented in the schema, including the tag examples, the query keyword format and the 200-character limit, and the GET/POST/PUT/PATCH/DELETE method mapping. The description adds no parameter detail beyond what the schema provides, 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?

The description states a specific verb and resource ('Finds the right SemanticHub operation') and enumerates the searchable domains (goals, sources, clusters, results, workflows, knowledge bases, queue). It also names the follow-up tools (api_details, api_read, api_write), making it easy to distinguish from siblings like semantichub_search_articles.

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?

It clearly indicates this is the entry point for locating an operation and that the resulting operation_id must be passed to api_details, api_read or api_write. The method filter's GET-vs-mutation mapping is explained in the schema, though the description itself doesn't state exclusions such as when to skip search and call a read tool directly.

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 destructive/non-idempotent, but the description adds the key behavior an agent cannot infer: risky operations return confirmation_required with a handle, the user must be asked, and the identical call must be repeated with that handle. Categorizing which actions are 'risky' (deletions, external deliveries, paid AI work, delivery/source changes) is genuinely non-obvious 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?

Two sentences, front-loaded with purpose then the risky-action protocol. Every clause carries information; nothing is 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 values need not be described. For a generic dispatcher over a large operation surface, the description supplies the one piece of procedural knowledge needed to call it safely — the confirmation loop — leaving operation shapes to api_details as stated in the 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?

Schema coverage is 100% and the confirm parameter is already documented in detail, so the description has little room to add. It reinforces that the retry must be the identical call with the handle, but adds no field-level meaning 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?

States a specific verb+resource ('Runs an operation that changes the user's account') and enumerates the concrete action classes (goals, sources, workflows, starting work, deleting). This clearly separates it from semantichub_api_read and the search/details siblings.

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?

Establishes when to use it (any changing operation) and prescribes a precise workflow for risky actions. It stops short of explicitly saying to use semantichub_api_read for non-changing calls or naming semantichub_api_search as the source of operation_id, which the schema carries 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?

With readOnlyHint/idempotentHint already supplied by annotations, the description still adds real behavioral context: restricted sources return articles without full text, and the archive requires the Pro or Scale plan. That is exactly the kind of caveat an agent needs before promising full-text results, though response shape is left to the output schema.

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?

Four short sentences, front-loaded with the core action and followed by narrowing, paging, and two caveats. Every sentence carries information; the only mild redundancy is repeating the semantic/keyword distinction already in the schema.

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 an 8-parameter search tool with an output schema, the description covers what to search, how to narrow, how to paginate, default recency, the plan gate, and the restricted-source caveat. Complete enough to call correctly; only the sibling-routing guidance is absent.

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 every parameter including mode, since, cursor, goal_id, portal_id and include_expired is already documented. The description only restates the mode distinction and the cursor paging convention, adding little beyond the structured fields, 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 (searches) and resource (news articles in the user's account) and distinguishes two matching modes, semantic vs. keyword title words. It does not differentiate itself from siblings like semantichub_search_brain or semantichub_api_search, so it stops 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?

Gives useful context about defaults: only current articles are searched unless include_expired is set, and paging is done via next_cursor. However it never says when to prefer this tool over semantichub_search_brain or semantichub_api_search, leaving the agent to infer the boundary.

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, closed-world), and the description goes further by disclosing a hard gating condition (model access must be enabled) and a prompt-injection handling policy for returned fragments. It also flags that results are private user data that should not be relayed without consent — context an agent cannot derive from any structured field.

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 carrying distinct load: what it searches, when it works, and how to treat the output. The corpus definition is front-loaded and there is no filler or repetition of 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 an output schema present and full parameter coverage, the description need not explain return values, and the addition of the model-access prerequisite and untrusted-content handling closes the two gaps the structured data leaves open. A minor omission is what the agent should do if model access is not yet enabled, but the tool is otherwise adequately specified.

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 kinds, limit, and query are already fully documented in the schema. The description adds only the general "by meaning" framing, which reinforces that query is natural language but does not add format, syntax, or default details beyond what the schema states.

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?

"Searches the user's Brain by meaning: their own documents and notes" gives a specific verb (semantic search), a specific corpus (the user's private Brain content), and a mode (by meaning, not keyword). It does not explicitly contrast with the similarly-named sibling semantichub_search_articles, so the agent must infer that the Brain is the private store rather than the public articles index.

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?

It supplies a real prerequisite (model access must be enabled by the user in the panel), which tells the agent when this call will fail. It gives no guidance on when to prefer this over semantichub_search_articles or the api_search sibling, so the sibling choice is only implied by the corpus wording.

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?

Beyond the safety hints (readOnlyHint), the description provides deep behavioral traits, such as listing specific data points (daily and per-minute usage) and implementing a critical constraint ('Never returns the account e-mail').

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 highly efficient, using clear language to convey multiple complex pieces of information—functionality, safety, and best practices—in a compact format.

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 parameter-less introspection tool, the definition is maximally complete, addressing what the tool does, its constraints, and its intended use case.

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?

With zero input parameters, the description focuses entirely on defining the necessary context and the value delivered upon execution, thus fulfilling the role required of the tool definition.

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 defines the scope, detailing the reporting of account identity, plan, usage limits, and granted permissions, which sharply distinguishes it from search or data manipulation siblings.

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?

It provides explicit usage guidance by instructing the agent to 'Call it first to see what you are allowed to do,' establishing a clear operational prerequisite.

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