Starlecta influencer tools

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

Goes well past the readOnly/openWorld annotations: states latency, that only up to two matches are returned (sometimes one or none), the exact card ordering (relevance, then engagement, then followers), that no score is returned, what the ranking field means, and that an optional safety object with flagged/reason can withhold details for privacy. That is unusually complete behavioral disclosure.

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?

Front-loads the input contract, then response shape, then ranking and safety. It is a single dense block with no filler, though the parenthetical ordering list is packed tightly and the undefined 'detailed mode' phrase adds mild ambiguity.

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 full burden and does it: return cardinality, card contents, ordering, missing score, ranking field, and the safety object are all explained. Minor gap: 'detailed mode' is referenced but no such parameter exists, which could confuse an agent.

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%, but with only one parameter the schema already constrains type and length. The description still adds real meaning beyond that: accepted languages (Turkish or English) and the fact the sentence is interpreted as filters and niche words rather than matched literally.

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?

Names a specific verb+resource ('AI search for influencers') and explains the input is a natural-language sentence read as filters and niche words. It never explicitly contrasts itself with the sibling 'search_influencers', so the agent must infer the AI/natural-language vs keyword distinction.

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?

Implies when it fits (free-text need, 2-200 characters, Turkish or English) and warns of cost (~30 seconds in detailed mode), but gives no explicit when-not or 'use search_influencers instead' routing despite six siblings with overlapping search semantics.

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 and openWorldHint, and the description adds genuinely new behavioral context: a live (uncached) read, a hard follower threshold that changes success behavior, a daily quota, and the interpretive note 'Not a score'. It doesn't say what happens for private or under-threshold accounts, which would be the natural next disclosure.

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?

Front-loaded with the verb, resource, and return surface, and nearly every clause carries information (eligibility, quota, metric list, sibling routing). The telegraphic fragments ('Not a score. Limited daily.') are dense but slightly ragged to read.

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 compensates by enumerating return fields including sample sizes ('with n') and dated metrics. Combined with the eligibility gate and quota note, an agent has enough to call it correctly; missing only error/failure behavior and any auth prerequisites.

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% with a single well-documented handle parameter including a regex pattern, so the schema does the work. The description adds only the implicit constraint that the account must be public and 10k+; it offers no syntax or format detail 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 and resource ('Reads one public Instagram account live') and immediately enumerates the returned metrics, so the agent knows exactly what the tool produces. It also distinguishes itself from the closest sibling by naming lookup_influencer and describing the difference (daily-tracked accounts show more there).

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 concrete eligibility ('Public accounts with 10,000+ followers'), a rate constraint ('Limited daily'), and a routing rule to lookup_influencer for accounts Starlecta tracks daily. It stops short of an explicit 'use this instead of search_influencers/compare_influencers when...' statement, so some inference is still required.

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 and openWorldHint=false, yet the description still adds meaningful context: aggregate figures only with no creators named (privacy/aggregation behavior), no authentication required, and that the optional day returns an earlier snapshot. Missing only edge-case behavior (invalid date, days with no data).

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 dense sentence that leads with the resource and packs the return payload efficiently, with operational notes (optional day, no key) at the end. The run-on construction slightly impedes scanning but no sentence is wasted.

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 usefully enumerates the metrics returned, and the sole parameter is covered, so an agent has enough to call it. Only gap is failure/empty-result behavior for an out-of-range or data-less day.

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 already documents the single optional day parameter including its format and 'latest day when omitted' default. The description's 'returns an earlier day' restates rather than extends that meaning, 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 concrete resource (the brand/shopping platform of the day on Instagram in Turkey) and enumerates the report contents, so an agent can distinguish it from the influencer-focused siblings without opening 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?

The description conveys context (daily aggregate report, 'no key needed') and the day-override behavior, but never names an alternative or a when-not-to-use condition against siblings like trend_cloud or ai_search_influencers. Usage must be inferred from scope 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=true and openWorldHint=false, so safety and scope are covered. The description adds that results are on the same method and dates and lists returned metrics, but it does not clarify what 'method and dates' means operationally or how missing handles are handled.

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 front-loaded sentence with no wasted words. It states the comparison, the fairness condition, and the output metrics efficiently.

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 low-complexity, two-parameter read-only tool with complete schema coverage and annotations, the description gives enough context to call it and lists the returned metrics. The only gap is the unclear reference to 'method and dates' without corresponding parameters.

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%, and both parameters are documented as Instagram handles with optional @. The description does not add parameter semantics beyond what the schema already provides, so the baseline 3 is appropriate.

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 a side-by-side comparison of two influencers and names the compared metrics, so the resource and operation are understandable. It does not explicitly differentiate itself from siblings like lookup_influencer or search_influencers, which keeps it from 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?

The description implies the tool is for comparing two influencers but gives no explicit when-to-use guidance, prerequisites, or alternatives. An agent must infer that this is the right tool when two handles are already known.

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 establish read-only and non-open-world behavior, and the description adds useful context: the card is public, data is tracked daily, engagement rate has a date, and status can be open, tracked, or not_listed. It does not cover failure or rate-limit behavior, but it goes meaningfully beyond the annotations.

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 compact sentences with no wasted phrasing. The resource and returned fields are front-loaded, followed by the status detail.

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, but the description lists the important return fields and status values, which is enough for a simple single-record lookup tool. A little more detail on the exact response shape would be needed for a perfect score.

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 schema description coverage is 100%, with the schema already explaining that the handle may be provided with or without @. The description adds no additional parameter guidance, so the baseline of 3 is appropriate.

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 identifies the resource as a public card for one Instagram influencer and lists the fields it contains, which distinguishes it from list/search siblings. It stops short of explicitly naming alternatives or stating 'retrieve by handle,' but the purpose is still easy to infer.

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?

Usage is implied: use this for a single influencer card rather than for search or comparison. However, the description does not explicitly say when to choose this tool over search_influencers or ai_search_influencers, so the agent must 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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful behavior: results are capped at a count plus at most two 'open cards', and er_measured is described as measured-engagement-only. However 'open cards' is undefined and there is no note on default behavior with zero filters.

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 compact sentences with no filler. The ordering is slightly off — the return value is front-loaded ahead of what the tool actually does — but nothing is wasted.

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 5-parameter tool with no required params and no output schema, the description does convey the key return shape (count plus up to two cards). It still leaves the undefined 'open cards', the all-optional default behavior, and result capping rationale unexplained.

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 only 20% (category only), so the description must compensate; it partially does by explaining er_measured ('measured engagement only') and restating the tier enum values. It adds nothing for followers_min/followers_max bounds semantics (inclusive? units?) beyond self-explanatory names.

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 leads with a return-value statement ('Count of matching influencers and up to two open cards') rather than stating the action; the verb 'search' exists only in the name/title. The filter list does imply a filtered influencer search, but nothing distinguishes it from siblings like ai_search_influencers or lookup_influencer.

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 ai_search_influencers, lookup_influencer, or compare_influencers, and no prerequisites or exclusions. The only usage-ish signal is the phrase 'measured engagement only', which constrains one filter but does not route the agent among alternatives.

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 declare readOnlyHint=true and openWorldHint=false, and the description is consistent with both. It adds genuinely useful context beyond the annotations: the rolling 7-day window, that results are aggregate counts only, and that no key is required. It does not describe result size or ordering, which keeps it from a 5.

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 dense sentence, front-loaded with the returned content and scope, with no filler. It is long but every clause (time window, metrics, aggregate-only, no key) carries 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?

With no parameters, no output schema and light annotations, the description fully carries the burden and does so: it explains what is returned, the time window, the metric types, and the aggregation/auth posture. Nothing needed 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. 'additionalProperties: false' on an empty object confirms no hidden inputs.

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 the resource precisely: rising hashtags with post counts and most-shared products, platforms and brands with share counts over a rolling 7-day window. This clearly sets it apart from the influencer lookup/search/compare siblings, which none of them touch trend aggregates. It lacks an explicit action verb ('get'/'fetch'), but the returned content 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?

The 7-day window implies when the data is applicable, but there is no explicit 'use this when' statement or mention of alternatives. Usage is inferable from the scope rather than stated.

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