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

No annotations are provided, so the description carries the full behavioral burden, and it discloses very little. 'Run the agent' hints at an LLM-backed, non-deterministic and potentially costly invocation, but latency, cost, determinism, and failure modes are never mentioned; 'what the news means for the subject' gives only a vague sense of the output. The existence of an output schema spares it from describing return values, which limits the penalty.

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 short and front-loads the core purpose before the input alternatives and enumerations. The telegraphic 'role: ... language: ru or en' style is efficient, though slightly cryptic and mixed with the usage sentence.

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 tool with a required profile_id, zero annotation coverage, and zero schema descriptions, the definition is thin. It never explains what profile_id is or why it is required, nor what 'the subject' refers to, and it gives no behavioral context for an agent-run analysis.

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, and it does partially: it clarifies the event_id-versus-title/text alternative and lists allowed values for role and language that are absent from the schema (role has no enum despite the description enumerating eight values). However, it omits url, publisher, and critically the required profile_id, leaving several parameters undocumented anywhere.

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 says it will 'Run the agent: what the news means for the subject,' which conveys that this is an analysis/interpretation tool rather than a raw feed, distinguishing it implicitly from siblings like news_feed and list_events. However, 'Run the agent' is vague phrasing and the subject of the analysis is never defined, so an agent cannot be fully certain what the tool produces without reading the 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?

'Give an event_id, or a title and text' explains how to supply input but says nothing about when to choose this tool over news_feed, list_events, or search_research. There are no exclusions, no prerequisites, and no statement of when interpretation is warranted versus simply fetching news.

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 full burden: it does not say whether this is a read-only lookup or an expensive model-backed query, whether it can fail on unknown insight_ids, or whether there is any rate/cost implication. The only behavioral hint is the phrase 'in this session', implying session-scoped state, which is useful but thin.

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 text is a single short fragment with no padding, so there is nothing to trim. But brevity here comes from under-specification rather than precision – it omits the verb and any operational detail the agent needs.

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. Still, for a two-parameter tool with zero schema coverage and no annotations, the definition leaves the agent guessing about the source of insight_id and the tool's execution characteristics.

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% for both parameters, so the description must compensate and does not: it never clarifies that insight_id is an identifier for a previously produced insight (or where to get one), nor what form the question should take. At most, 'an insight produced in this session' weakly implies the provenance of insight_id.

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 fragment conveys intent – posing a follow-up question about an insight already produced in the session – which distinguishes it from siblings like search_research or analyze_news. However, it is a noun phrase with no verb, so it never states the action (ask/submit/generate an answer) or what the tool actually does with the question.

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 on when to use this versus the sibling tools, and no prerequisites stated beyond the implied 'insight produced in this session'. Nothing tells the agent whether the insight_id must come from a prior call in the same session or how to obtain it.

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 carries the full behavioral burden, and it only discloses the response encoding (JSON). It does not state that the operation is read-only, what happens when profile_id is unknown (empty result vs error), any authorization or visibility constraints, or rate limits.

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 short sentence with the resource and return format front-loaded and zero filler. It is efficient, though its brevity reflects under-specification rather than disciplined compression.

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 tool is a simple single-parameter read with an output schema, so return values need not be described. However, with no annotations and 0% schema coverage, the description should at minimum identify what profile_id refers to and confirm read-only semantics, which it omits.

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% for the single parameter, so the description needed to define what profile_id actually is (a numeric user id, a handle, an internal identifier, a subject slug). It adds no meaning beyond the bare property name and required flag.

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 full profile of a subject as JSON" names a specific resource (a subject's profile) and implies retrieval of the complete record, which separates it from the listing behavior implied by the sibling list_profiles. It stops short of explicitly contrasting with list_profiles or stating what 'subject' means, so it is clear but not sibling-differentiating.

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 when-to-use guidance at all: nothing says when to call get_profile instead of list_profiles, get_trace, or search_research, and no prerequisites (e.g., needing a known profile_id) are stated. The agent must infer the use case purely from the name.

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 full burden. It does useful work by disclosing the returned payload (tool calls, model calls, timing, cost, review findings), from which an agent infers this is a read-only, non-destructive lookup. It does not state what happens if the insight_id is unknown, whether traces can be partial or truncated, or any permission requirement.

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 defines the resource in the first clause and then enumerates its contents. No filler, no restatement of the tool name, and the most important information leads.

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 tool is simple (one required parameter) and an output schema exists, so return-value explanation is not strictly required. However, with no annotations at all and no parameter documentation in the schema, the description should say more about the ID's origin and read-only/error behavior. It is adequate but leaves the single input under-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 0% and the input schema gives no title or description for insight_id. The description only indirectly implies the parameter by saying 'How an insight was produced,' and never says what an insight_id looks like, where to obtain one, or whether the ID must come from analyze_news. For a zero-coverage schema this leaves a real gap.

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 names the resource concretely (the provenance of an insight) and enumerates the contents of the trace: 'every tool call and model call with timing, cost and review findings.' An agent can tell this is a provenance/audit retrieval tool. It lacks an explicit verb and does not name or contrast any sibling, but the siblings listed (news_feed, list_events, get_profile, analyze_news) are distant enough that confusion is unlikely.

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 or when-not-to-use statement is given, and no alternative is named. Usage is only implied by the phrase 'How an insight was produced' — i.e. call this to explain or audit an existing insight. An agent must infer that this is an after-the-fact explainability call rather than a discovery call.

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 full behavioral burden and delivers almost nothing. It does not disclose ordering ('latest' by what field?), whether results are capped or paginated, freshness/refresh behavior, or any auth or scope constraints. The existence of an output schema excuses return-value description, but the operational behavior remains opaque.

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 short sentence with no filler and a front-loaded noun phrase. It is efficient, though the brevity is closer to under-specification than to disciplined conciseness.

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 tool is simple (one optional integer, output schema present), which lowers the bar, but the description still fails to explain the recency semantics behind 'latest' or how this differs from news_feed. For a list tool with an unlabeled limit parameter, that is a meaningful shortfall.

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 one parameter, limit, with 0% schema description coverage, so the schema contributes no semantics. The description only hints at relevance via 'latest' and says nothing about what limit counts (events, days?) or what the default of 20 means in practice, leaving a real gap for the single knob the caller can turn.

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 phrase 'Latest news events in the store' identifies the resource (news events) and implies a listing/recency behavior, but never states a verb and never distinguishes the tool from the sibling news_feed or analyze_news. An agent can guess it fetches a recent-events list, but cannot tell why it would pick this over news_feed.

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 when-to-use guidance, no exclusions, and no reference to any alternative. With news_feed and analyze_news in the sibling set, the lack of routing guidance leaves the selection decision entirely to guesswork.

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 full behavioral burden, yet it only enumerates return fields. It does not state that the call is read-only, whether it returns all profiles or a filtered set, or anything about ordering or pagination.

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?

It is a single short sentence with no wasted words, but it is structured as a colon-separated field list rather than a front-loaded statement of what the tool does. It is concise to the point of under-specification.

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 need not explain return values, and its field list is reasonable duplication. However, for an agent deciding between this and get_profile, the definition omits the listing scope and any usage context, leaving it only minimally 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 is no parameter semantics to add beyond the schema. The baseline of 4 applies for a no-parameter tool.

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 phrase 'Subjects available for analysis: id, kind and a short summary' identifies the resource (profiles/subjects) and its returned fields, but it reads as a noun phrase rather than a clear action. It never states that it lists all profiles, and it does not explicitly differentiate itself from the sibling get_profile.

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 when-to-use guidance at all: no indication of whether this should be called before get_profile, no mention of alternatives, and no prerequisites or context. The agent must infer usage purely from the tool name.

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 supplied, the description carries the full behavioral burden and it partially covers it: it discloses ordering ('strongest links first') and that each result carries a ranking code plus a reason. It does not state that this is a read-only operation, how results are capped or paginated, or whether an empty profile yields an error versus an empty list. Adequate but with real gaps for a zero-annotation tool.

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 short sentences with the ranking behavior front-loaded and the delegation hint second; nothing is padded. The clipped 'since: YYYY-MM-DD' fragment is efficient but reads as a note rather than prose, which slightly weakens the structure.

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 needn't be described, and the description does note the per-item reason field that a caller will see. However, for a three-parameter tool with no annotations and no schema documentation, leaving `top` and the meaning of profile_id's 'subject' role unexplained is a meaningful omission.

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 for all three parameters. It explains the format of `since` (YYYY-MM-DD) and loosely identifies `profile_id` as 'the subject', but `top` — the result limit, defaulting to 10 — is never mentioned, leaving a caller to infer whether it is a count, a scope, or something else.

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 resource and scope: stored news concerning a subject, ranked strongest-links-first with a reason per item. It also implicitly separates itself from analyze_news by naming that tool for follow-up depth. It stops short of a clean verb-led statement ('Which stored news concern the subject' is a fragment), but the retrieval purpose 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?

It gives concrete routing guidance: use analyze_news on an event_id taken from this list to get full insight, which tells the agent this is the shallow discovery step and that tool is the depth step. It does not state exclusions (e.g. when to prefer list_events or search_research instead), so the when-not half of the guidance is missing.

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 supplied, so the description carries the full behavioral burden, yet it says nothing about ranking, matching semantics, permissions, or result volume. The presence of an output schema covers return shape, but nothing about how search behaves is disclosed.

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 clean sentence with no filler, so nothing is wasted, but the brevity comes at the cost of substance rather than from tight editing of a complete definition. It is under-specified rather than efficiently concise.

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 described, but a search tool with no annotations, 0% parameter coverage, and no usage routing guidance leaves the agent guessing about both query semantics and when to invoke it. The definition does not do enough for a tool with two undocumented inputs.

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% for two parameters, and the description does not compensate: it does not explain what a query string matches against (titles, bodies, authors) or that limit defaults to 3 and caps result count. Both parameters remain semantically opaque.

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 names a specific verb (Search) and resource (the institution's research documents), which cleanly separates it from the news-, event-, and profile-oriented siblings. It stops short of explicitly contrasting with any named alternative, so it is clear but not maximally distinguishing.

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 on when this tool should be chosen over ask_followup, analyze_news, or other siblings, and no stated preconditions or exclusions. The agent must infer the use case entirely from the one-line purpose.

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