lian-chain-intelligence

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

With no annotations, the description carries the full burden, and it does disclose the return keys (available_now, coverage, requires_trigger), implying a cheap read-only preflight. However it never explains what 'requires_trigger' means or what an agent should do when coverage is false, and gives no cost/auth/latency context.

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 gating instruction is front-loaded and the whole thing is two short sentences. The '[v1.6.0]' version tag and the full bilingual duplication are wasted tokens that carry no selection value.

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 and no annotations, so the description must carry the return-value semantics — it names the three response fields but does not explain how to interpret them or what the agent should branch on. Adequate for a simple 2-param gate, but not 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 description coverage is 100%, so the schema already documents 'entity' and 'entity_id' including the either/or relationship. The description adds nothing beyond that, 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?

The description says to 'check coverage status' and names the returned fields (available_now, coverage, requires_trigger), which hints at a preflight/availability gate, but it never states what the availability is *of* — presumably intel coverage for an entity, which the agent must infer from the sibling names. It is identifiable but not a specific verb+resource statement.

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 '先查 / check first' framing plus 'Then chain/signal/brief' gives explicit sequencing: call this before the sibling intel tools. The sibling references are truncated ('chain/signal/brief' vs intel_chain/intel_signal/intel_brief), but mapping is obvious. No when-not guidance is 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?

With no annotations, the description carries the full behavioral burden. It does disclose one genuinely useful trait — 'rule template' / 'not an LLM' implies deterministic, non-generative output — which goes beyond the name. But it says nothing about what is returned, whether a snapshot is written (the 'heal' param hints at a side effect), permissions, or cost.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but a chunk of the length is spent on a version tag and a near-verbatim bilingual repetition that adds no information. The substantive claim ('which gap combination is present, not an LLM') is there but buried behind jargon.

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?

Four all-optional parameters, no output schema, and no annotations mean the description must explain what a call returns and what happens with an empty argument list (default entity? default window?). It explains neither, leaving an agent unable to predict the result of the tool.

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 each of the four parameters (heal, entity, window, entity_id) is already documented in Chinese. The description adds no syntax, defaults, or mutual-exclusivity detail beyond the schema, so 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?

The description names what is being checked — a rule-template-assembled 'gap combination' across landing, commercialization, technology, chain-master and cross-border dimensions — so a reader can roughly guess it returns an intel brief about which gaps are present. However, there is no clear verb+resource framing, the bilingual duplication and bracketed version tag obscure the core statement, and it never explicitly distinguishes this from the many intel_* siblings.

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 call this versus intel_category, intel_chain, intel_chain_master, intel_signal or any other sibling, nor any mention of prerequisites or context of use. The 'not an LLM' note is a disclaimer, not 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?

No annotations are provided, so the description carries the full disclosure burden. It does add genuine behavioral context that structured fields don't: the pack is 'fat' and expensive in tokens, and atoms should be used to cut cost. It says nothing about read-only vs write, response shape, or size/limits of the payload.

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?

Very short and the cost warning is front-loaded, but the content is duplicated wholesale in Chinese and English and prefixed with a version tag '[v1.6.0]' that adds no selection or invocation value. Roughly half the text is redundant restatement.

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, no annotations, and optional params, the description is the only place an agent can learn what this aggregate returns — and it never says. Beyond the token-cost hint there is no indication of payload contents, size, or result structure, which is a significant gap for a bundle tool whose whole purpose is returning a lot of data.

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 slug and its category alias. The description adds nothing about the parameters — it doesn't say whether slug/category are optional filters or what happens when both are supplied (the alias relationship is only in 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?

It conveys that this is the aggregate 'full category pack' as opposed to the atomic pieces, and names the sibling tools it bundles. But '品类全包（肥）' never says what the pack actually contains or what verb the tool performs — it's a noun phrase, not a stated purpose, so an agent knows it is 'everything' without knowing what 'everything' is.

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 routes the agent away from this tool and toward intel_category_opportunity / _supply / _demand_pull / _migration when token budget matters, which is concrete and actionable. It stops short of stating the complementary condition (when to prefer the full pack over the atoms), but the direction 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?

With no annotations, the description carries the full behavioral burden and falls short. It discloses only that the output is an atomic demand-pull slice and that public results omit chains, but it says nothing about permissions, data freshness, return shape, or other operational 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?

The text is short but cluttered with a version tag '[v1.6.0]', an internal code 'L-153a', and bilingual duplication. These fragments do not help an agent decide when or how to call the tool, so the structure is not meaningfully front-loaded.

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 is too sparse. It notes the demand-pull scope and the public no-chains rule, but it does not explain what the returned signals/chains represent or what an agent should expect.

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 slug and category are already documented as strings, with category noted as an alias of slug. The description adds no additional parameter meaning, which is acceptable at baseline 3 when the schema does the heavy lifting.

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 largely restates the tool name with internal jargon: 'demand_pull slice only' and '只出需求倒逼段（signals/chains）'. It hints that the tool returns a demand-pull segment and excludes chains publicly, but it does not clearly state what resource is being queried or what the slice actually contains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or when-not-to-use guidance is given. The fragment '公开无 chains' implies a public limitation, but there is no direction on alternatives such as intel_demand or intel_chain, nor any prerequisite context.

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, but it does disclose one real behavioral trait: non-Pro callers receive only teaser/locked content while full data requires an upper tier ('全是需壁垒'). That gating semantics is valuable and not inferable from the schema, but return format, partial-result behavior, and error modes are entirely unexplained.

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?

Short, but not concise in the useful sense: two internal identifiers (v1.6.0, L-153a), a bilingual restatement, and jargon ('壁垒') consume the whole budget while the actual purpose is never front-loaded.

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 no-annotation, no-output-schema tool in a crowded category family needs the description to explain what data is returned and how it differs from ~15 siblings. The one useful hint (tier gating) does not make up for the missing purpose and result 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?

Schema coverage is 100% and both parameters (slug and its alias category) are documented in the schema, including that category is an alias. The description adds nothing about parameter usage, but baseline 3 applies since the schema does the heavy lifting.

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 reduces to an internal code ('L-153a 原子：技术迁移层' / 'Atomic: tech_migration') plus a version tag, without a verb or statement of what the tool actually returns or does. An agent can guess it relates to technology-migration data for a category, but nothing distinguishes it from siblings like intel_category_supply or intel_tech_dir.

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 or when-not-to-use guidance relative to the many intel_category_* and intel_tech_* siblings. The only contextual phrase ('Non-pro: teaser/locked only') describes entitlement, not selection criteria.

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. '已按档裁剪' (trimmed by tier) hints at filtering/truncation but never says what the tier is, what gets cut, or how to avoid trimming — an agent cannot predict what it will receive. Nothing on auth, data freshness, or response 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?

It is short, but the leading '[v1.6.0]' and 'L-153a 原子' tokens are internal noise that consume the front-loaded position where the actual purpose should be. The useful content ('海外/价差/切入点') arrives after the jargon.

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 and no annotations, so the description should explain what the 'opportunity surface' returns; the parenthetical examples are too thin to tell an agent what fields to expect or how 'trimmed by tier' affects results. Zero required parameters also goes 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 coverage is 100% and both parameters (slug, and category as its alias) are documented in the schema, so the schema does the heavy lifting. The description adds no parameter guidance, which is acceptable at this coverage level but leaves the alias/slug relationship solely to 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?

The description does state the output surface — category opportunity, listing overseas / price spread / entry points — which distinguishes it from sibling slices like intel_category_supply or intel_category_demand_pull. However, internal identifiers ('L-153a 原子') and 'already trimmed by tier' obscure what the tool actually does, and there is no clear verb or resource framing an agent can act on.

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 says 'opportunity slice only', which hints at the boundary with other intel_* slice tools, but no alternative is named and no condition for choosing this over intel_category, intel_category_demand_pull, etc. is given. The agent must infer usage 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?

No annotations are provided, so the description carries the full disclosure burden. The one behavioral hint, '已按档裁剪' (pruned according to tier), is meaningful but unexplained — an agent cannot tell what tier means, whether data is filtered or truncated, whether the call is read-only, or how fresh the figures are. For an unannotated tool this is a substantial gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but the space is spent on version and code identifiers ('[v1.6.0] L-153a 原子') rather than on the scoping or routing information an agent needs. The genuinely useful clause ('supply slice only') arrives at the very end instead of being front-loaded.

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 annotations and no output schema, the description is the only source of behavioral information, and it does not say what the 'supply slice' returns, what 'whole units / parts schematic' means concretely, or how the tier-based pruning affects results. An agent can form only a rough guess about when and how to call it.

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 the schema already documents both parameters ('Category slug' and 'Alias of slug'), including the alias relationship. The description adds no parameter-level detail beyond that, 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?

The bilingual text does identify the resource as a category supply output ('只出品类供给' / 'supply slice only'), which distinguishes it from demand-oriented siblings such as intel_category_demand_pull. However, it never states a verb or the form of the operation, and the leading tokens '[v1.6.0] L-153a 原子' are internal identifiers that tell an agent nothing about what the tool does.

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?

'supply slice only' implies this is the supply-side counterpart to the demand tools, so the selection logic can be guessed. But there is no explicit when-to-use, when-not-to-use, or named alternative (e.g. intel_category vs intel_category_demand_pull), and no hint about how it relates to intel_availability or intel_chain, leaving routing 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 burden; it does disclose an auth prerequisite ("需 Key/Requires key") and names the three output fields, which is real value. But it omits whether the call is read-only, whether it is slow/rate-limited, and how the three segments are combined or ordered.

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 content is short, but it is duplicated verbatim in Chinese and English, and the "[v1.6.0]" version tag and the unresolved "≈get_chain" reference are noise. Front-loading the field list is good; the padding is not.

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?

Without an output schema, the brief field enumeration (timeline, delta_days, vs_prior) partially compensates, but it never explains what those fields contain or what the tool returns overall. A dangling comparison to a non-sibling tool leaves the agent without a reliable routing decision.

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 both parameters carry descriptions (entity, entity_id with the ent_ prefix and a two-of-one-or-both rule), so the schema does the work. The description adds nothing about which identifier to prefer or whether entity_id is more precise – 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?

"全链/Full chain" plus the field list (timeline, delta_days, vs_prior) hints at a chained-intelligence summary, but the resource is never named concretely beyond a metaphor. It also references "≈get_chain", which is not a sibling tool (the closest is intel_chain_master), so the intended differentiation is muddled.

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 call this versus intel_chain_master, intel_brief, or intel_signal. The "requires key" note is a prerequisite, not usage guidance, so the agent must guess.

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

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

With no annotations provided, the description does disclose one real behavioral trait: public/free tiers withhold source URLs, which tells the agent output may lack citations. However, it says nothing about whether this is a read-only lookup, what authentication or tier the caller holds, or how results are paginated or scoped.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and front-loaded, but it duplicates every sentence verbatim in Chinese and English, roughly doubling length without adding information. Every sentence would earn its place if the content were substantive; here the redundancy undercuts the brevity.

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 three-parameter tool with no output schema and no annotations, the description leaves the return shape, the meaning of 'published', and the relationship to the other intel_* tools entirely unstated. The one piece of useful context, URL redaction on free tiers, is not enough to call this 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 description coverage is 100%, so entity, category, and entity_id are already documented with examples in the schema. The description adds no interpretation of these parameters, which is the baseline 3 when the schema carries the explanatory load.

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 restates the tool name ('链主倒逼' / 'chain-master push') without a verb or resource indicating what the tool actually returns or does. The only added semantics are cryptic filter notes ('承接方不是定点供应商'), which don't resolve into a describable operation, so an agent cannot distinguish it from intel_chain or intel_supply siblings.

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, when not to, or which of the fifteen intel_* siblings covers an adjacent question. The note that the receiving party is not a designated supplier is a domain claim, not invocation 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 burden. It usefully discloses a public-data limitation (first 3 signals, no chains) and that data is anonymous, but it does not state whether the operation is read-only, whether authentication is required, or what happens on missing entities.

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 appropriately short and front-loads the version and domain concept. However, the English sentence largely duplicates the Chinese text, so several phrases do not add new 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?

For a 4-parameter tool with no annotations and no output schema, the description covers the main modes and public truncation limit. It still leaves gaps around sibling differentiation, output structure, and operational behavior, so it is only minimally complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all four parameters. The description adds mode-level meaning by explaining list=1 and entity/slug usage, but it omits the entity_id alias and otherwise stays at the baseline provided by 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?

The description identifies a specific domain function: demand-pull analysis over category signals/chains, with two modes (list entities or look up one entity/slug). That is clear enough for an agent to understand what the tool does, but it does not differentiate this tool from the sibling intel_category_demand_pull, which sounds like it may serve the same purpose.

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 provides parameter-mode guidance: use list=1 to list entities, or pass entity/slug to retrieve a specific one. However, it gives no explicit when-to-use guidance relative to alternatives such as intel_category_demand_pull, nor does it state exclusions or prerequisites.

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 and does disclose real behavioral traits: exact return fields, the as-of vs rolling-window semantics, tier-dependent source URLs (non-pro omits them, pro includes them), and JSON-only output. It still omits auth requirements for the pro tier and 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?

Front-loaded with purpose and return fields, and every behavioural note (as-of date, source URL tiering) earns its place. But the content is duplicated verbatim in Chinese and English, and the '[v1.6.0] L-179' prefix is noise that dilutes the opening.

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 and no annotations, so the description must be self-sufficient; it covers return fields, date semantics and tiering, which is most of what an agent needs. It leaves undefined what an 'S code' is, the units of 'gap', and how a caller knows whether it is pro or non-pro.

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 the schema already documents both properties, making 3 the baseline. The description reinforces 'slug' as required but never mentions the `category` alias, and 'required' actually conflicts with required: 0 in 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?

Names a specific resource and scope: atomic global race for one category, returning domestic S, foreign S, gap and as-of date. The phrase 'Atomic' and the enumerated return fields let an agent distinguish this from broader aggregate siblings like intel_category or intel_brief. It stops short of explicitly naming which sibling to use instead.

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 a prerequisite ('必传品类 slug') and an important usage caveat — the date is as-of based, not a rolling 30-day feed — which steers interpretation. However, no alternatives are named and no when-not-to-use condition is given relative to the many sibling intel_* category tools.

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 does carry the key safety signal itself: 'Writes this snapshot' discloses a state-mutating side effect. But it says nothing about what the write overwrites, whether it is idempotent, whether a permission/credential is required, or what happens when no prior snapshot exists — all material for a write 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?

Each language version is a tight two sentences with the mutation note last, so the phrasing itself is efficient. However, the full text is duplicated in Chinese and English and prefixed with a version tag, which inflates length without adding information an agent can act on.

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 description covers the operation and the three result categories well enough to call the tool, and no output schema exists to explain them further. It is still thin for a write tool with no annotations: preconditions (prior snapshot required), overwrite semantics, and required permissions are all absent.

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 documents entity, entity_id, and the 7–90 day window including their exclusivity relationship. The description adds no syntax, default, or behavioral detail about any parameter, 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?

The description names a specific operation: comparing gap types against this site's last snapshot, with the three outcome buckets spelled out (gone / still here / new). It reads clearly against the sibling list, none of which share the snapshot-diff framing, though 'gap type' and 'heal' remain undefined domain jargon.

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 states a precondition implicitly (there must be a prior snapshot) but gives no explicit when-to-use guidance, no exclusions, and does not route the agent to or away from any sibling such as intel_availability or intel_signal. Nothing tells the agent when this is the right call versus the other fifteen intel_* tools.

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

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

No annotations are provided, so the description carries the full behavioral burden. It does not state whether the tool is read-only, what permissions are required, how results are ordered, or what the response looks like; it only gives a rough taxonomy of gap types.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, but it duplicates the same content in Chinese and English and leads with a version tag rather than a clear purpose statement. The content earns some place, but the bilingual repetition and cryptic '≈list_signals' phrase reduce efficiency.

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 annotations and no output schema, the description should do more to explain behavior and return values. It gives a partial content taxonomy but leaves an agent unable to confidently determine result shape, safety profile, or how this tool relates to its many 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 description coverage is 100%, so entity, window, and entity_id are already documented in the schema. The description adds no parameter meaning beyond what the schema provides, which is the baseline expectation when coverage is complete.

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 indicates that the tool surfaces 'rule gaps' and lists categories such as landing, commercialization, and tech, so the general resource is inferable. However, '规则缺口（≈list_signals）' is cryptic jargon and does not clearly distinguish this tool from the many intel_* siblings or explain what a 'rule gap' actually is.

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 explicit guidance on when to use this tool versus alternatives such as intel_brief, intel_category, intel_chain, or the other intel_* tools. The '≈list_signals' note is ambiguous and does not establish a clear selection rule.

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, but it does disclose a genuinely useful behavioral trait: results are truncated to the top 2 entries on public/free tier and complete only for pro. It says nothing about whether the call is read-only, what a matrix row contains, ordering, or rate/auth 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?

Very short and front-loaded, but the content is duplicated verbatim in Chinese and English, and the "[v1.6.0]" prefix is noise that consumes attention without helping selection. The tier constraint, the most useful sentence, is buried at the tail.

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 read tool with no annotations and no output schema, the description needs to say what comes back — columns, what "heat" means, ordering, or row identity — and it does not. An agent knows only that it gets up to 2 (free) or more (pro) rows of unspecified shape.

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?

Only one optional parameter (date) exists and schema description coverage is 100%, including the "omit for today" default. The description adds nothing about the date parameter, so the baseline of 3 applies — the schema is doing all the work.

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 identifies a resource (a "tech-word heat matrix" / 技术日报词矩阵) but the noun is jargon — an agent cannot tell what the rows or values actually are. It is closer to a restatement of the name plus a tier note than a specific verb+resource statement, and it does not differentiate itself from siblings such as intel_tech_dir or intel_tech_launch.

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?

"与 /tech-daily 同一批行" hints at a related endpoint but no when-to-use / when-not-to-use rule or sibling alternative is given among the 16 intel_* tools. The only actionable guidance is the gating note (free = top 2 rows, pro = full table), which is about entitlement rather than tool selection.

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 has to cover the safety profile, and it provides unusually strong behavioral detail: data freshness windows (news 90 days, papers 24 months), Pro vs non-Pro result caps, omission of source URLs for non-Pro, and a JSON-only return. It does not specify how authentication or subscription tier is determined, so one gap remains.

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 content is dense and front-loaded, but it is stated twice: the Chinese block and the English block repeat identical facts. The version tag "[v1.6.0]", internal code "L-179", and "原子" are noise that does not help an agent decide or invoke.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema and no annotations, so the description carries the full burden, and it delivers: it names the returned fields (stage, category, clues), the vintage of the data, the tier-dependent truncation, and the return format. Only edge-case behavior for invalid or conflicting identifiers 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?

Schema description coverage is 100% (both name and dir_id documented with examples), so the baseline is 3. The phrase "传 dir_id 或方向名" does add modest value by implying either identifier alone is sufficient, but the schema marks no parameter as required, and the description does not resolve what happens if both are supplied or neither is supplied.

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 tool is described as "原子：一个技术方向" (an atomic tech direction) looked up by dir_id or name, and it states what it returns: stage, category, and clues. The scope is clear, but the description never distinguishes this tool from similar ones like intel_category or intel_tech_daily.

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 only says "传 dir_id 或方向名" (pass dir_id or name), which is a parameter hint rather than guidance on when to use the tool. It gives no context, no "not for" exclusions, and no alternatives; tier rules (max 2 clues for non-Pro) only imply differentiated use and are not spelled out.

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

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

With no annotations provided, the description carries the full disclosure burden, and it delivers: a 48-month window, tiered behavior (non-pro returns at most 2 items without source URLs; pro returns the full set with sources), and JSON-only output. It omits auth/subscription prerequisites and how the tier is determined.

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 content is useful but the same payload is repeated in Chinese and English, roughly doubling length without adding information. The version and internal ID prefix '[v1.6.0] L-179' is noise that leads the description instead of the purpose.

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 and no annotations, so the description must carry both behavior and return shape. It does describe what is returned (conversion actions with dates) and the tiering of results. It leaves out how the tier is determined and whether errors occur when the slug 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?

Schema coverage is 100%, so both parameters are already documented. The description adds that slug is mandatory, but it never explains that 'category' is an alias of 'slug', which is the one semantic point where schema and description both fall short.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource and scope: an atomic tech-launch lookup for one category slug, returning conversion actions such as equity-for-technology, capital contribution, and joint ventures, each with dates. This distinguishes it from sibling tools like intel_tech_daily and intel_tech_dir. It does not explicitly name which sibling to use instead, so it stops short of 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 instruction '必传品类 slug' (slug is required) clarifies that the tool needs a slug, even though the schema shows required: 0. It also states a 48-month window, which sets expectations. It gives no explicit when-not-to-use guidance or named alternative among the many category siblings.

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