TrendsFast

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

Goes well beyond the annotations by disclosing the credit ceiling (5), the zero-cost path when no findings exist, that it saves a result, and that it makes no provider/model calls or hidden fresh research. These are real behavioral traits an agent cannot get from readOnlyHint=false/destructiveHint=true. The gap is that it never explains why destructiveHint is true or what the 'saved result' overwrites, which matters for a destructive-flagged call.

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 purpose and cost cap, which is good. The middle sentence is a long run-on that lists five answer_status values and three output fields, and since an output schema exists, that enumeration partially duplicates structured data rather than adding decision-relevant 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?

The presence of an output schema excuses not explaining return values, and the description does cover cost and side effects. But for a tool with 3 required params, a large nested niche/filters object at 0% schema coverage, and a sibling project_context tool, the absence of any guidance on supplying context, product selection, or filter scope leaves the definition 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% across a deeply nested input object, so the description carries the full explanatory burden — and it does not. It implies the 'question' and 'max_credits' parameters but says nothing about input.niche, input.filters, the 'product' enum (customers/niche/competitors/formats/search), context_id, or include_global/include_adjacent, all of which materially change the call.

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: 'Answer a bounded question using saved intelligence', which is meaningfully distinct from the discovery-oriented siblings (discover_trends, niche_trends). It enumerates the question domains (competitors, complaints, feature requests, hooks, keywords) so the agent can recognize eligible questions. It never names a sibling to route against, so differentiation is inferred rather than explicit.

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?

'Bounded question' and the domain list imply when this tool applies, and the 'Maximum 5 credits' plus 'An answer with no findings costs nothing' give a cost-based decision rule. However, there is no explicit when-not-to-use guidance, no mention of how this relates to trendsfast_discover_trends or trendsfast_read_result, and no statement that a prior project context (context_id) is expected.

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 readOnly, idempotent and non-destructive, so the safety profile is carried structurally. The description still adds value by disclosing the zero-credit cost of the call and the account-level ('shared') scope, which the annotations do not express.

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 the verb, resource, returned fields and cost caveat all present. No filler, nothing to trim.

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?

Zero-argument read with an output schema, so the description needn't document returns or parameters. It covers what is left: what account state is read, the 'shared' scope, and that the call is free.

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?

Zero parameters, so the baseline is 4. The description correctly claims nothing in the way of arguments, and 'shared' usefully signals there is no user/workspace selector to pass.

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?

Specific verb 'Read' plus specific resource 'shared REST/MCP credit balance' with the exact sub-fields returned (monthly/prepaid split, reservations, pause state). None of the sibling tools touch account state, so an agent can route to it 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?

'Without spending credits' implies this is the cheap upfront check before calling paid query siblings, but the connection is never stated and no sibling is named. Usage is inferable rather than instructed; there are no explicit exclusions or 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?

Strong for its length: discloses the credit cap (max 5), zero provider calls, that it saves a result and may debit credits, and that UNAVAILABLE is returned instead of an empty channel when no permitted observation exists. These add real context beyond the annotations (readOnlyHint=false, destructiveHint=true), which already flag the write/credit-debit profile. It does not explain idempotency behavior or how the saved result is retrieved.

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?

Five short, front-loaded sentences with no filler; the cost and scope facts come early. The telegraphic style leaves some sentences ambiguous ('No new source research'), which is a minor cost to comprehension.

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 description covers cost, scope and channel behavior. But for a three-parameter, deeply nested discovery tool with zero schema descriptions, key inputs (question, product, context_id, filters, request_id) go entirely 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 0% across a deeply nested input with question, product, context_id, channels, scope, filters and a twenty-field niche object. The description mentions scope, channels and 'Product DNA' in passing but never explains what question, product, context_id or the filter block do, so it fails to compensate for the coverage gap on a high-complexity 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?

The description gives a concrete capability statement: answer one question across global, core and adjacent scope and every source channel in a single call. It signals breadth (all scopes, all channels) which implicitly differentiates it from narrower siblings like global_trends or niche_trends, but it never names those alternatives or states 'trends' as the resource unit, so the differentiation stays implicit.

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?

'Global scope needs no Product DNA' is a real prerequisite hint, and 'No new source research' sets a boundary. However, there is no explicit when-to-use guidance versus trendsfast_ask_trends, global_trends or niche_trends, nor any exclusion rule telling the agent when this broad, credit-consuming call is the wrong choice.

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=false, destructiveHint=true, idempotentHint=true and openWorldHint=false; the description reinforces and explains those by disclosing the credit debit, the save-on-charge behavior, the request_id replay rule ('same request_id returns that saved result without a second charge'), and the 1-credit/non-provider-call cost model. It does not explain what the destructiveHint=true risk concretely is (beyond writing a saved result), 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?

What-it-does and cost are front-loaded, and most sentences carry information. However, the ranking sentence ('then US, UK, Canada and Australia, then Europe, alternating sources') is dense and hard to parse, and output-shape detail (data.brief groups, per-item guidance) crowds out guidance about the input parameters.

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 lengthy explanation of data.brief and item guidance is partly redundant, while the genuinely complex part — the nested input filter object — gets no coverage at all. Cost and idempotency are complete, but the filter vocabulary an agent must supply is not.

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 schema is a nested object with 13+ undocumented input fields (signals, platforms, categories, observed_from/to, history_days, evidence_quality, compare_to), none of which the description clarifies. It does add real meaning for request_id (idempotency key) and max_credits (per-query cap), which is why it is not a 1.

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: query the shared saved trend index, and adds the differentiator 'without Product DNA', implying the sibling tools that do require product context. It doesn't name a sibling explicitly, so the contrast with discover_trends/niche_trends/ask_trends must be inferred.

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 'without Product DNA' clause implies this is the path for product-agnostic global exploration, but there is no explicit when-to-use/when-not or named alternative. The credit/idempotency mechanics are covered, but call routing between this and the four other trend-query siblings is left to inference.

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?

The description adds substantial context beyond the annotations: per-lens credit debits, the no-charge failure path, that a Search call sends the buyer question to four external models with no brand included, and that Formats pulls transcripts. This is consistent with the write/destructive annotations ('Saves a result and may debit credits'). What is missing is any statement of result size, latency, or what a repeat identical call returns despite idempotentHint=true.

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 undifferentiated block of dense prose with nested clauses that frequently require re-reading ('A Customers or Trending call, or a read without product, also returns data.communities when...'). Large portions are spent describing return payload fields (data.communities, data.items[].topic_history, data.ai_answers, data.brief) that an output schema already covers, which is exactly the padding this dimension should penalize.

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 mode/cost/error model is well covered and the existence of an output schema excuses the description from explaining returns, so the core call path is callable. However, for a tool with a very large nested filters surface and 12 alternative filter fields, an agent still has no guidance on how the filters interact with the chosen product lens or how to scope a run beyond the defaults.

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 0% schema description coverage the description must carry the whole burden, and it does explain context_id, the product enum's cost model, and a few niche fields (communities, competitor_handles, competitor_domains, keywords), plus the CORE vs ADJACENT rule. But the entire filters object (signals, categories, evidence_quality, observed_from/to, history_days, compare_to, content_types), request_id, include_global, and most niche fields (jobs, market, topics, audiences, exclusions, capabilities) go entirely unexplained.

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 opening sentence gives a concrete verb and resource ('Rank evidence against confirmed project context or explicit temporary niche') and the body enumerates the five product lenses with their credit weights, which is genuinely distinguishing. It never names or contrasts the obvious siblings (trendsfast_discover_trends, trendsfast_global_trends, trendsfast_ask_trends), so an agent must infer the boundary itself.

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 spelled out through decision branches rather than exclusions: no product caps at 3 credits and does no new research; a product requires the confirmed context_id; a product paired with a typed niche is refused with PRODUCT_REQUIRES_CONTEXT and charges nothing. That is real when/when-not guidance, but there is no explicit 'use this instead of X sibling when...' routing.

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 readOnly, idempotent, non-destructive and closed-world, but the description adds genuinely new behavioral facts: no credit debit, no context mutation, no new research is triggered. It also discloses that a missing-context state may be returned rather than an error, which helps the agent interpret results; only minor gaps remain (e.g. auth/prerequisite for a 'connected' project).

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 with zero waste: capability first, the returned handle second, the cost/side-effect disclaimer last. Every sentence earns its place.

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-value explanation is not required, yet the description still flags the two outcome shapes (confirmed niche context vs. explicit missing state) and the key field name. For a zero-parameter read tool this is 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 the baseline is 4; there is nothing for the description to disambiguate. The description correctly adds no parameter noise and instead explains the single return handle (context_id) that callers must carry forward.

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 (read) and resource (connected project name, ID, confirmed niche context), plus the explicit missing-context fallback state. It also names the downstream consumers (niche and Ask queries) that accept the returned context_id, which clarifies its role among siblings, though it does not contrast against the other siblings like credit_balance or read_result.

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 line 'Returns the context_id that niche and Ask queries accept' implies this should be read before issuing those queries, giving clear usage context. It does not state explicit exclusions or when NOT to call it, so it falls short of the 5 bar.

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 readOnly/idempotent/non-destructive, yet the description adds genuinely non-obvious behavior: no credit is debited, no research is re-run, and source permissions, retention and context are revalidated at read time. Those last points materially affect whether an agent can rely on a cached result.

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 the capability and closed by the constraints. Dense but every clause carries information; only minor loss from packing three modes into one 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?

An output schema exists so return values need no explanation, but for a 3-optional-param tool with no schema descriptions, the definition should clarify the selection rule between result_id, request_id and cursor. It identifies the modes but leaves their interaction underspecified.

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 description must compensate, and it partially does by mapping each of the three params to a mode (saved result → result_id, paginate → cursor, exact accepted request → request_id). It does not state that the params are mutually exclusive or whether one is required, which matters given 0 required fields.

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 specific verbs and resource: read a saved result, paginate it, recover an accepted request ID. The phrase 'No credit debit or research' implicitly distinguishes it from the research siblings (ask/discover/global/niche trends) without naming them explicitly.

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 enumerates three modes (read, paginate, recover) but never says which parameter selects which mode or when to prefer recovering a request_id over a result_id. Usage is implied by the verb list rather than stated as a decision rule.

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