PrismFact

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 that every returned value has a source and date, that absence is represented by five distinct categories (found, none, unknown, not_provided, withheld), and that up to 100 INNs are accepted. This goes well beyond the schema, though edge cases like malformed INNs are not covered.

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 three sentences, front-loaded with the core purpose, followed by the key behavioral nuance about absence markers and then the input limit. Every sentence earns its place with 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 simple two-parameter tool with no output schema, the description covers the essential aspects: what data is returned, how absence is represented, and input constraints. It stops short of fully explaining sibling trade-offs or the exact effect of the 'want' parameter, but it is largely complete for the tool's simplicity.

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

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

The schema already has 100% parameter description coverage for 'inn' and 'want'. The description adds meaningful parameter behavior by stating the exact limit of one hundred comma-separated INNs, reinforcing the 'inn' parameter's semantics. This exceeds the high-coverage baseline.

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 title and description clearly state the tool retrieves all known facts about a subject by INN, with each value including a source and date. This distinguishes it from siblings like prism_find, prism_nearby, and prism_needs by its focus on INN-based fact lookup, though it doesn't explicitly name alternatives.

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 gives clear context: use it to fetch facts for up to one hundred INNs, and the five-way absence marking helps decide whether to repeat the question or go elsewhere. It lacks explicit when-not-to-use guidance or named sibling alternatives, but the intended scenario is well implied.

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

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

Without annotations, the description carries the full burden. It discloses a notable behavioral trait: each response includes a denominator (total subjects on the territory) and warns that the share is meaningless without it. However, it omits other important context like whether the operation is read-only, pagination behavior, or any side effects, which are relevant for a 14-parameter query tool.

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 first sentence is informative and front-loaded. The second adds a useful quirk. The third sentence ('Verification is sold by everyone...') is a vague marketing phrase that doesn't earn its place and detracts from clarity. Overall length is acceptable but not every sentence carries weight.

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 tool with 14 parameters, no output schema, and no annotations, the description is insufficient. It fails to explain the return structure beyond the denominator, does not mention pagination/sorting (though sort is a parameter), and doesn't clarify the domain (business entities). The presence of sibling tools with overlapping territory themes increases the need for clearer context.

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 71%, so the baseline is 3. The description adds a high-level summary of filter dimensions (activity, size, tax regime, revenue, debt) that maps to several parameters, but it doesn't explain parameter syntax, units, or how parameters combine. It provides marginal value beyond the schema's own field descriptions.

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

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

The description states the tool's function: identifying subjects on a territory by activity type, size, tax regime, revenue, and debt. The title reinforces this as 'detection' ('Обнаружение субъектов'). However, it doesn't explicitly use a verb like 'search' or 'find', and the subject type (UL/IP) is only in the schema, making it slightly less clear than it could be.

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 vs alternatives. The final sentence 'Verification is sold by everyone, detection is not sold by anyone' cryptically contrasts verification with detection, hinting at a difference from prism_ask, but it doesn't state 'use this for detection' or name any alternative. No mention of prism_nearby or prism_needs at all.

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, so the description carries the full burden. It discloses a data limitation (the sign-TIN link is a hypothesis), but doesn't say whether this operation is read-only, what it returns, or any preconditions.

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 focused sentences with no wasted words, and the key distinction from a registry is front-loaded. The wording is slightly cryptic but efficient.

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 tool with no annotations and no output schema, this description leaves out the core function and parameter usage. It only covers the data nature and one limitation, which is insufficient for an agent to select and invoke the tool 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?

With only 17% schema coverage, the description should compensate but gives no parameter semantics. It only indirectly hints that lat/lon are coordinates, leaving q, category, limit, and radius_m undefined.

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 explains what kind of data the tool serves ('Слой карты, а не реестр') but never states the action directly. The title implies nearby retrieval, but the description lacks an explicit verb like 'list' or 'find'.

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 implies use when you need coordinates-based places and notes the registry can't answer because it has no coordinates, but provides no explicit when-to-use or alternatives among sibling 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 must clarify side effects, but the line 'Дыру можно закрыть, принеся факт — он проходит те же ворота записи' ambiguously suggests a write/closing capability while the input schema accepts only the optional 'days' parameter. It does disclose the three-party aggregation threshold, but omits whether the call itself is read-only, what output to expect, or any permission/rate-limit 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 description is compact (two sentences) and places the core definition first. It is slightly metaphorical ('нарисованный чужими вопросами') but not 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?

For a simple one-parameter tool the description conveys the main purpose and threshold, but because there is no output schema it does not explain the shape of the returned gaps, and the 'days' window is only documented in the schema. This is adequate but leaves some operational ambiguity.

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 sole parameter 'days' is fully described in the input schema ('окно, по умолчанию 30'), so the baseline is met. The description itself adds no additional meaning to the parameter.

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 title 'Чего у нас нет, а спрашивают' plus description 'Список дыр... что спрашивали и на что мы не ответили' clearly identifies a read-only listing of unresolved user requests. It distinguishes itself from siblings (prism_ask, prism_find, prism_nearby) by defining the content as gaps that have been requested and not answered, with a specific threshold.

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

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

The description implies usage when identifying unmet needs and mentions the minimum request threshold, but it does not explicitly state when to prefer this tool over prism_ask/prism_find or provide exclusions. The 'дыру можно закрыть' line hints at a follow-up action but doesn't name the alternative.

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