BuildFeed

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

No annotations are provided, so the description carries the burden — and it does disclose the returned content dimensions rather than just restating the name. A zero-parameter 'get' tool is inherently a safe read, and the description makes clear it reports corpus-wide coverage metrics. It doesn't explicitly state read-only or return format, but the behavior is well conveyed.

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, each earning its place: the first enumerates the returned aggregates, the second gives usage guidance. The scope statement is front-loaded and 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?

With no output schema and no parameters, the description must describe what comes back — and it enumerates the metric categories thoroughly. An agent can decide to call this and know what to expect without further information.

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 no argument surface for the description to clarify. No gaps exist here.

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 (aggregate statistics for the entire BuildFeed corpus) and enumerates exactly which aggregates — total videos, channels, categories, topics, views, date range, enrichment coverage. It also distinguishes itself from per-video siblings like get_video.

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 an explicit condition for use: high-level 'how much data / how fresh' questions, contrasted against 'per-video detail'. It stops short of naming the specific alternative tools (get_video, list_videos), but the routing intent is unambiguous.

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 of behavioral disclosure. It says nothing about return format, concurrency, rate limits, or authentication, and critically omits any mention of pagination/truncation despite a maxChars parameter. The one behavioral hint — 'bounded window' — is vague and predates knowledge of the actual constraints.

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, no filler. The primary purpose leads and the sibling-routing guidance follows immediately. Every clause 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?

A 4-parameter tool with no annotations and no output schema needs the description to cover parameter meaning, default behavior, and return shape. The description covers only routing rationale; it omits parameter semantics, defaults, and output contract, leaving significant gaps for an agent to call it correctly.

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 all four parameters (videoId, maxChars, startSeconds, endSeconds) are undocumented beyond their JSON types. The description mentions only 'bounded' and 'for one video', which hints at videoId and the time/character bounds, but it names no parameter and provides no format, default, or boundary semantics. With a 0% coverage gap the description should compensate, and it does not.

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?

Clearly states a specific verb and resource ('Get a bounded transcript window for one video'), and explicitly differentiates from the sibling search_transcript_passages by describing itself as the follow-up context-inspection tool. Loses a point only because 'bounded window' is slightly jargon-ish, but the resource (transcript) and scope (one video, bounded window) are 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?

Explicitly names the alternative (search_transcript_passages) for discovery and states the exact condition for using this tool instead: after selecting a video, to inspect surrounding context. This is a textbook when-to-use/when-to-use-alternative statement.

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 discloses the substantive behavioral fact for this tool — precisely what content is and isn't returned (transcript text excluded) — and 'Get' implies a safe read. It omits secondary traits such as permission requirements or error behavior when an ID/slug is invalid.

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 tight sentences, front-loaded with the purpose and content scope before the workflow guidance. Every clause carries information; nothing is padding.

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?

There is no output schema, so the description must describe the return payload — and it does so field by field, including the notable omission of raw transcript. For a single-parameter read tool this is complete enough to invoke correctly.

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 'id' parameter is fully documented in the schema, including the 11-char example and slug alternative. The description restates that same duality ('either an 11-character YouTube video ID or a BuildFeed article slug') without adding format, validation, or failure semantics, 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 and resource ('Get full detail for a single BuildFeed video') and enumerates the returned content: description, channel info, stats, categories, topics, TLDR, key takeaways. It also distinguishes itself from get_transcript by explicitly noting the raw transcript text is excluded, so an agent can tell it apart from a sibling without opening a 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?

Gives clear placement in a workflow: 'Use this after search_videos/list_videos to drill into one specific result,' naming both discovery siblings explicitly. It stops short of a direct negative routing statement (e.g., 'for transcript text use get_transcript'), though the exclusion note hints at 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?

No annotations are provided, so the description carries the full burden and does well: it discloses the dual return shape (index of weeks vs. full detail), the ordering ('most recent first'), and the date-key format. It does not cover permissions, error behavior for a nonexistent week, or any rate limits, which keeps it short of 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?

Four tightly packed clauses, each carrying distinct information: purpose, no-date mode, with-date mode, and usage intent. The most decision-relevant fact (mode branching) is front-loaded immediately after the purpose statement, 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 two-parameter read tool with no output schema and no annotations, the description covers both invocation modes, the date-key format, and the ordering of results. It leaves the shape of a 'full roundup detail' and the behavior on an invalid or nonexistent week unspecified, which is a minor but real gap.

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 both parameters are already documented in the schema, including the YYYY-MM-DD pattern and the 'omit to list available weeks' semantics. The description restates the date-mode behavior and pattern without adding format or constraint detail beyond the schema, matching the baseline 3.

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 ('Get BuildFeed's weekly roundup content') and then splits the tool's two distinct behaviors: index listing without a date vs. full week detail with one. This is unambiguous and clearly separable from siblings like get_stats, get_video, and list_videos, which serve different resources.

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?

Explicitly names the query types it serves ('what happened this week' or historical week-by-week summary questions), which is concrete when-to-use guidance. There are no sibling alternatives covering roundups, so no exclusions are needed, but it stops short of stating when this tool 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?

No annotations are provided, so the description carries the burden, and it does disclose the return payload (category names plus per-category video counts) even though no output schema exists. 'List' implies a non-mutating read, but it stops short of stating idempotency, auth needs, or whether the taxonomy is fixed server-side.

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 tight sentences: the first front-loads what is returned, the second gives the reason to call it and the downstream consumers. No filler, no restatement of the name.

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 zero-parameter discovery tool with no output schema, the description covers what comes back, why it matters, and which sibling tools consume the result, which is everything an agent needs to place this call correctly in a workflow.

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 and the baseline of 4 applies. It correctly avoids inventing any parameter or filtering semantics.

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 (list) and resource (BuildFeed's video categories) and even enumerates the returned items (AI, VC, Startup, Product, Design, Tools) with video counts. It is immediately distinguishable from siblings like list_channels or list_topics, which cover different taxonomies.

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?

Explicitly prescribes when to use it: 'to understand the taxonomy before filtering search_videos/list_videos/list_channels by category,' naming three concrete downstream siblings and the category filter that links them. The agent knows both the purpose and the follow-on 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?

With no annotations, the description carries the full burden. It usefully discloses the sort order (by video count descending) and what each row contains (video counts, categories), which goes beyond the schema. It does not confirm the read-only, non-destructive nature of the call or any pagination/truncation behavior beyond the limit cap already in the 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?

Two sentences, purpose first, usage second, with no filler. The only mild redundancy is the restatement of "BuildFeed covers" versus "tracked by BuildFeed" in 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 a simple read-only list tool with two fully documented optional parameters and no output schema, the description covers purpose, use case, filtering, and return shape plus ordering. An agent has enough to call it correctly; only the absence of explicit read-only framing and sibling routing keeps it from a 5.

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 the schema already explains both limit and category, including defaults and the hard cap. The description only restates the category filter at a high level ("optionally filtered to a category") and adds no syntax or semantics beyond the schema. 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 and resource ("List YouTube channels tracked by BuildFeed") and adds scope details: video counts, categories, and sorting order. It does not explicitly differentiate itself from siblings like list_categories or list_videos, but the resource noun is unambiguous enough for selection.

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?

"Use this to discover which creators BuildFeed covers" gives a concrete use case, and the optional category filter narrows the condition. There is no statement of when NOT to use it or which sibling to prefer for adjacent needs (e.g., listing videos vs. channels).

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, the description carries the full behavioral burden. It discloses what the operation returns (video counts, aliases, content-type distribution, audience labels), which is genuinely useful given there is no output schema, but it says nothing about read-only safety, pagination, or result-set 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?

Two dense sentences with the resource and scope front-loaded and the return contents trailing. No filler, though it could be slightly tighter.

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 filtering list tool with no required parameters and no output schema, the description adequately covers what the tool returns and the grouping concept. The main gap is the absence of alternative-tool routing, which is minor for a straightforward enumerator.

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 67%, so most parameters are documented in the schema itself (group, minVideos have descriptions; limit does not). The description adds no syntax or filtering semantics beyond what the schema 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?

States a specific verb (List) and resource (canonical topic clusters) scoped to the BuildFeed archive, and enumerates example families, which makes it distinguishable from list_categories and list_channels. It never names those siblings explicitly, but the resource noun does the differentiation work.

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 statement of when to use this tool versus list_categories or list_channels, no prerequisites, and no exclusion criteria. The only context offered is the scope phrase 'full BuildFeed archive,' which is not routing 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?

With no annotations, the description carries the full disclosure burden. It usefully states the return shape (compact records without transcript or description text) and notes that videos outside the rolling cache have qualityScore 0 and commentCount 0. However, it does not mention pagination limits behavior or permissions, so it is helpful but not exhaustive for a mutation-free list tool with zero annotation coverage.

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, front-loaded with purpose, then return shape, then the routing alternative. Every sentence earns its place with no redundancy.

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 compensates by describing the returned record fields and what is omitted. The tool is a simple read with four well-documented params, so completeness is nearly full; only minor operational details (e.g., default/pagination behavior) are left implicit.

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 both parameters are already fully documented in the schema. The description reiterates the category filter and sort options but adds no new syntax or constraints beyond what the schema provides, which matches the baseline for high-coverage schemas.

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 (List) and resource (curated BuildFeed videos) with scope and the filter/sort capabilities. It explicitly names the sibling it is not (search_videos), so an agent can discriminate without opening either 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?

Provides explicit when-to-use (browse recent/top videos) and when-not/alternative (use search_videos for a specific topic). Nothing 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?

With no annotations, the description carries the full behavioral burden. It discloses useful traits — cross-video search, relevance ranking, timestamped excerpt output — but says nothing about default result count, result caps, ranking behavior, or whether results are read-only/paginated. Adequate but incomplete for a search tool with zero annotation coverage.

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 tight sentences with the core behavior front-loaded and the usage guidance second. Every phrase earns its place, no padding or restated boilerplate.

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 6-parameter search tool with no annotations, no output schema, and 0% schema coverage, the description is complete on purpose and usage but leaves parameter behavior (especially limit and the filter enums) and result-set characteristics undocumented. Minimum viable given the tool's complexity.

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 6 parameters, so the description should compensate, yet it mentions none of them — not the limit cap/default, not that topic/audience/category/contentType act as filters, not the enum semantics. The self-describing enum values carry the load, but the description adds no parameter 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 specific verb and resource (search transcript passages) and immediately describes the return shape: relevant timestamped excerpts across multiple videos. It implicitly but clearly distinguishes itself from metadata-level siblings like search_videos by noting answers 'may not appear in a title or summary.'

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 explicit use cases (evidence, quotations, implementation details, questions not answerable from title/summary), which effectively routes the agent away from the summary/title siblings. It stops short of naming an alternative tool or stating when NOT to use this one.

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, and it does disclose meaningful behavior: what fields are matched, how results are scored and ordered (relevance, then recency), and that results come with summaries. It does not state that the operation is read-only, nor anything about result shape beyond summaries or behavior when nothing matches, which keeps it short of 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?

Two sentences, both load-bearing: the first front-loads what the tool does and how results are ranked, the second handles routing versus the sibling. No filler or redundancy.

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 4-parameter search tool with full schema coverage but no annotations and no output schema, the description covers what an agent needs: scope, matching fields, ordering, and routing to list_videos. The main remaining gap is return format, which is only hinted at ('with summaries').

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% - query, limit (default 20, hard cap 50), since (ISO 8601), and category (enum) are all documented in the schema. The description adds only indirect context by enumerating the fields the query matches against; it adds no syntax or format detail beyond the schema. 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 and resource ('Full-text search over BuildFeed's curated AI/startup/VC YouTube video library') and goes further by naming the fields scored (title, topics, TLDR, channel, takeaways) and the ranking rule (relevance, then recency). It explicitly contrasts itself with the sibling list_videos, so an agent can distinguish the two without opening either 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?

Gives both when-to-use ('user asks about a specific topic, person, product, or company and you need to find relevant videos with summaries') and when-not ('not when you just want to browse everything'), plus names the alternative tool and the condition that selects it. Nothing 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.