IRI Lab

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

Annotations already declare this as a safe, idempotent, closed-world read, so the description is not burdened with that. It adds real value by enumerating the specific content returned (API address, key format, docs, key acquisition path), which compensates for the absence of an output 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?

One compact sentence, front-loaded with the subject and then a tight enumeration of the four returned items. Nothing is repeated and no filler is present.

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, non-destructive lookup with no output schema, the description supplies exactly what an agent needs: the fact that it returns connection/credential information and what that information covers. It could only be stronger by stating that no authentication is required to call it or noting the response format.

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 of 4 applies; there is no parameter meaning for the description to elaborate. The description correctly implies a parameterless, single-shot lookup.

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 resource (IRI Gateway connection details) and enumerates what it returns: API address, key format, documentation, and where to obtain a key. The purpose is clear and clearly distinct from the siblings (prices, ratings, job/model/subscription search), though it never explicitly says so.

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

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

Usage is only implied: an agent can infer this is the tool to call when it needs to configure a client or find credentials. There is no explicit when-to-use statement, no mention of prerequisites, and no named alternative among the 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?

Annotations already declare this read-only, idempotent, closed-world and non-destructive, so the safety profile is covered. The description contributes genuinely useful domain context that annotations cannot — currency (rubles) and pricing unit (per 1M input/output tokens) — but it does not say whether all models are returned by default or how the result is shaped.

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 a single short sentence with zero filler, and the most important detail (what is priced and in what unit) is front-loaded. It is arguably over-terse, omitting a verb, but nothing is wasted.

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

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

For a low-complexity read-only lookup with full schema coverage and clear annotations, the description covers the essentials. However, with no output schema, it never indicates that the result is a list of models with input/output price fields, nor whether an empty query returns everything — a gap an agent would notice at call time.

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 single 'query' parameter is fully documented in the schema (100% coverage) as an optional name filter, so the schema already does the work. The description adds nothing about matching semantics (substring vs exact, case sensitivity), 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 resource — IRI Gateway model prices in rubles per 1M input and output tokens — so an agent knows exactly what data it returns. It lacks an explicit verb (no 'get/return') and never contrasts itself with the neighboring search_models or get_model_rating tools, so sibling differentiation rests entirely on the name.

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 guidance at all: nothing says to call this before cost estimation, nor when to prefer it over search_models or get_model_rating. The only filterable behavior is implied by the schema, not the description.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety behavior needs no restating. The description does add one piece of real context beyond them: the data is an external LLM Stats benchmark ranking rather than internal data. It says nothing about ordering, tie-breaking, or what happens when a vendor has no ranked models.

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

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

A single front-loaded sentence identifying the resource, the data source, and the two modes of use, with no filler. It is appropriately sized for a two-parameter read tool, though the appended mode clause reads slightly compressed.

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, fully annotated, zero-required-parameter read tool with no output schema, the definition covers the essentials. However, as a ranking tool it never states what the ordering is or what a returned row represents, which is the main thing an agent would want before calling 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%, so both parameters are already documented and the baseline is 3. The description adds only modest meaning: 'одного разработчика' clarifies that vendor scopes the leaderboard to a single developer's models rather than filtering results after the fact. It says nothing about limit's interaction with ranking order (top-N of what ordering).

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

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

States a concrete verb+resource: a ranking of neural-network models based on external LLM Stats benchmarks, either overall or restricted to one developer. That is clearly a read/rank operation. It does not name the sibling it differs from (search_models), so an agent must infer the boundary between 'ranking' and 'searching'.

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 clause 'лучшие модели в целом или одного разработчика' implies two usage modes (global leaderboard vs per-vendor leaderboard), which is the closest thing to when-to-use guidance here. There is no explicit statement of when to prefer this over search_models, and no exclusions or preconditions are 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?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that by naming the returned fields (role, company, city, salary, link), which compensates for the absent output schema, and by scoping results geographically. It still omits ordering and empty-result behavior, so it is not fully transparent.

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

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

A single compact sentence with the action, domain scope, and returned fields front-loaded. There is no redundant or filler wording; every clause carries information.

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

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

For a three-optional-parameter read tool with no output schema, the description is nearly sufficient: it names the result fields and the geographic/domain scope. The remaining gap is the lack of routing guidance against the sibling search_* tools, which matters since several similarly named search tools exist.

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 all three parameters (limit, query, location) are already documented with examples in the schema. The description merely echoes that city and role are relevant, adding no syntax, matching behavior, or format detail beyond what the schema provides; 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 gives a specific verb ('Найти') and resource ('вакансии') and constrains the domain to AI/ML jobs in Russia, plus enumerates the returned fields (role, company, city, salary, link). It does not explicitly differentiate itself from siblings like search_models or search_subscriptions, though the resource noun makes the distinction reasonably inferable.

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 when-to-use or when-not-to-use guidance, nor any mention of the sibling tools (search_models, search_subscriptions) as alternatives. Usage is only implied by the domain scoping 'в сфере ИИ и машинного обучения в России', which an agent can infer but must not be told directly.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine value beyond that by disclosing what the result contains (rating place, context, gateway price, page URL), which is not derivable from any structured field since there is no output schema. It omits any note on result ordering or the limit's effect, which keeps it from a 5.

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

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

A single front-loaded sentence opening with the action verb, followed by a compact enumeration of returned data. No filler, no repetition, and the most decision-relevant information comes first.

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

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

With no output schema, the description carries the burden of explaining return values and does so adequately. Annotations cover the safety profile, and the schema covers parameters, so the remaining gaps are minor: no note on result ordering, pagination, or what happens when no model matches.

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 all three parameters — query, limit, only_gateway — are already documented in the schema. The description largely restates the query semantics (name or developer) and gestures at the gateway filter via the price mention, but adds no new syntax, matching rules, or limit behavior beyond what the schema provides. 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 gives a concrete verb and resource ("Найти нейросеть по названию или разработчику") and enumerates the fields returned — rating position, context, IRI Gateway price, page link. That is enough to distinguish it from the narrower siblings get_model_rating and get_gateway_prices, though it never names them explicitly.

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

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

Usage is only implied: the search-by-name-or-vendor framing plus the mention of rating and price suggests this is the broad discovery entry point, with the sibling tools as drill-downs. There is no explicit statement of when to prefer it over get_model_rating or get_gateway_prices, and no prerequisites or exclusions are 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?

Annotations already declare a safe, closed-world, idempotent read. The description adds real context beyond them: results carry a ruble price and a link, availability is constrained to payment from Russia, and fulfilment is performed by a human on the website, which correctly signals that no purchase can be executed through this tool. It does not cover result volume, ranking, or empty-query 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?

Three short sentences, front-loaded with the resource and scope, then examples, then return contents and the fulfilment caveat. Every sentence carries information; only minor fragmentation keeps it from a 5.

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 one-optional-parameter read tool with annotations and no output schema, the description covers scope, result contents, and the human-fulfilment limitation. The main residual gap is behavior with an omitted query (list-all vs. empty result) and its distinction from search_models.

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 single optional 'query' parameter is documented in the schema with an example. The description adds nothing about the parameter, but with full schema coverage the baseline of 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 states a specific resource and scope: subscriptions to AI services (ChatGPT, Claude, Gemini, Cursor) payable from Russia, returning price in rubles and a link. An agent can tell this is a catalog lookup rather than a model/job/pricing lookup. It does not explicitly contrast with siblings like search_models or get_gateway_prices, which keeps it from a 5.

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

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

There is no explicit when-to-use or when-not guidance, and no sibling is named as an alternative. Usage is only implied by the resource description; the agent must infer that this is the tool for purchasable subscription offers versus model metadata or gateway pricing.

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