High Signal

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds the 'current public' scoping constraint and the notion of a publication state, but does not say how the optional region parameter affects results or what the returned brief contains beyond date/state.

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 with no filler, stating the resource and key return facets. Appropriately sized, though it could have used the space to cover the region parameter.

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 explained, and the read-only annotations cover the safety profile. However, for a tool with an undocumented region parameter and no usage guidance against five sibling tools, the description leaves meaningful gaps.

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 schema has one parameter (region) with 0% description coverage, and the description never mentions it. This leaves the agent guessing whether region filters, scopes, or is required for retrieval semantics, so the description fails to compensate for the schema 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?

States a specific verb (Retrieve) and resource (the current public Daily Brief) with scope qualifiers (current, public) and enumerates the returned facets (edition date, publication state). It is clear, though it does not explicitly differentiate itself from siblings like get_daily_signals.

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 guidance on when to use this versus get_daily_signals or the other signal tools, and no mention of prerequisites or when-not-to-use. The agent must infer selection from the name alone.

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, destructiveHint=false and openWorldHint, so the safety profile is fully covered structurally. The description adds that results are 'evidence-qualified published' signals and scoped to an IST day, which is useful beyond annotations, but says nothing about pagination, default page size, or empty-day 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?

One front-loaded sentence with no redundancy; the scope and timezone qualifier come before any detail an agent would need.

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 and annotations cover the safety profile, so return values and side effects need no explanation. Still, with two undocumented parameters and no sibling routing, the definition is adequate but not complete for a tool sitting in a cluster of five signal-related siblings.

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 only 33%: date is documented, but limit and offset carry no descriptions in either schema or tool description. The description reinforces the IST timezone meaning of date, but leaves pagination entirely unexplained, which is the gap the low coverage requires it to fill.

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 ('Retrieve ... published signals') plus a clear scope ('for one IST day') and a qualifier ('evidence-qualified'). An agent can tell it returns a day's worth of signals rather than a single signal or a brief, but it never explicitly differentiates itself from get_daily_brief or search_signals.

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 and no alternatives named despite five closely related siblings (get_daily_brief, search_signals, get_signal). The agent must infer that this is the calendar-day retrieval tool while search_signals handles queries.

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, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact — the lookup is limited to a 'bounded recent' public feed — which warns that older or non-public signals may not resolve, but says nothing about miss/error 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?

A single front-loaded sentence with no filler; every clause (exact, published, bounded recent, public feed) carries scoping information.

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 no prose, and the feed-scope caveat is present. However, the sole parameter's format is left entirely to inference and no failure mode is described, leaving an agent under-informed on how to supply a valid slug.

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 schema description coverage at 0%, the single slug parameter is undocumented in the schema and the description only implies 'exact' matching without citing the slug format, the kebab-case pattern, or the 160-char limit. It adds minimal meaning beyond the parameter name itself.

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 (Retrieve) and resource (signal) with the qualifier 'exact published signal from the bounded recent public feed', which hints at slug-based lookup versus the search-oriented sibling. It does not name search_signals or get_signal_evidence explicitly, so the differentiation is inferable rather than stated.

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 word 'exact' implies this is the direct-lookup path when the slug is already known, distinguishing it loosely from search_signals, but no when-to-use, when-not-to-use, or alternative routing is spelled out. Usage is only implied.

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, openWorldHint=true, and destructiveHint=false, so the safety and repeatability profile is covered. The description adds only the constraint that evidence is tied to a published signal; it says nothing about result volume, pagination, or what happens when a slug has no linked evidence.

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 with no filler or repetition. It is efficient, though very spare for a tool whose routing relative to get_signal could be stated in a few more 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?

An output schema exists, so return values need not be described, and the read-only annotations carry the behavioral profile. What remains missing is the relationship to sibling tools and any expectation for slugs without evidence, leaving the definition minimally viable rather than 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 coverage is 0%, so the schema supplies only format constraints (pattern, length) with no semantic description. The description partially compensates by clarifying that the slug must be for an exact, published signal, which explains the required identifier's meaning but adds no detail about canonicalization or case handling.

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 ("Retrieve") and resource ("canonical evidence events linked to... signal slug"), making it distinguishable from get_signal, which returns the signal itself. However, it does not name or contrast any sibling explicitly, so the differentiation is inferable rather than stated.

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 tool versus get_signal, get_daily_signals, or search_signals, nor any explicit alternatives. The phrase "one exact published signal slug" hints that the slug must resolve to a published signal, but this prerequisite is not framed as usage 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, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds two useful behavioral points beyond that – results are paginated/'bounded' and represent 'live' (open-world) outcomes, plus a caveat about sample-size reliability – but omits auth needs, rate limits, or ordering 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?

Two short, front-loaded sentences with no filler; the primary purpose leads and the caveat follows. The phrasing is telegraphic enough to feel terse rather than fully clarifying, keeping it short of a 5.

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 explained in prose, which the description rightly does not attempt. But with two undocumented parameters and no sibling routing, the description is only minimally complete for a read tool in this family.

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 schema documents neither 'limit' nor 'offset'. The description only hints at bounding ('bounded') without defining the limit ceiling, default, or what offset paginates over, leaving both parameters materially under-specified.

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 gives a verb ('Retrieve') and a scope ('live prediction outcome buckets'), so the agent knows it deals with prediction results rather than raw signals. However, 'track record' is only restated as the jargon term 'outcome buckets', which is not self-explanatory and does not clearly distinguish it from siblings like get_signal_evidence.

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 only guidance is the interpretive caveat that small resolved samples are not calibrated confidence evidence. There is no statement of when to call this versus get_signal_evidence or get_daily_signals, and no prerequisites or exclusions are given.

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, openWorldHint=true — the safety and determinism profile is fully covered. The description adds one behavioral detail: results retain original publication dates, which is useful but not needed for call correctness. It adds some value beyond annotations but doesn't cover pagination behavior or result shape.

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?

Single sentence, front-loaded, no padding. Efficient for what it does say, though it's arguably too short for a 3-param search tool.

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 explained. But the tool has 0% parameter documentation and no differentiation from five siblings. For a search endpoint where query syntax and pagination matter, the definition is materially incomplete.

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% — none of the three parameters (q, limit, offset) have descriptions. The tool description mentions no parameter at all: no query syntax, no limit semantics, no offset/pagination behavior. With zero schema documentation and no description compensation, an agent has to guess at 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 vague verb+resource ('search the feed') but the qualifier 'bounded recent' is imprecise and doesn't distinguish from siblings like get_daily_signals or get_signal. An agent can't tell what 'bounded' or 'recent' means in practice.

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 when-to-use guidance, no alternative routing. With five sibling tools (get_daily_brief, get_daily_signals, get_signal, get_signal_evidence, get_track_record), the description should say which one this replaces or complements, but offers nothing.

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