mitracore

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 does disclose useful behavior: the check is private, it returns a verdict, a score and a sha256 'ready for signing', which tells the agent this is an analysis/audit step. However, it does not state whether any files are written, what permissions are needed, or how the privateness is enforced.

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, front-loaded with the action and resource, then the enumerated checks, then the return contract. No filler, though the return-value sentence overlaps with the existing output schema.

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 output schema exists so verdict/score/sha256 need not be re-explained, and the description is adequate for a single-path audit tool. It is still thin on the one input parameter and on prerequisites, leaving gaps for an agent deciding whether 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?

One required parameter at 0% schema description coverage, so the description must compensate and does not. It never says what 'path' points to (a directory containing SKILL.md? the file itself?) or what format is expected, beyond the implicit mention of SKILL.md.

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 (проверить/check) and resource (SKILL.md) and enumerates exactly what is inspected: structure, triggers, secrets, prompt-injection, broken links. The purpose is unambiguous, but it never distinguishes itself from similarly-named siblings such as trust_report or verify_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?

The word 'Приватно' (privately) hints at a local/offline check, but there is no explicit when-to-use, when-not-to-use, or alternative (e.g. why trust_report instead). The agent must infer when this tool applies.

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. Calling it a 'quote' implies a pure computation with no persistence or side effects, but that is never stated, nor is whether the result is a non-binding estimate or an actual billing event. Minimum-viable disclosure for a read-style compute 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?

A single front-loaded sentence that states the operation, the inputs it consumes, and the contrast with a price table. No filler, nothing that could be cut without losing meaning.

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

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

An output schema exists, so return values need not be described, and all five optional (default 0) parameters are at least named. Still missing for an agent to call it confidently: whether omitting parameters means zero consumption, what units are expected, and whether the quote has billing consequences.

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

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

Schema description coverage is 0% and the schema exposes only bare titles, so the description does real work: 'токены, CPU, байты, записи, внешние вызовы' maps cleanly onto tokens, cpu_seconds, bytes_out, storage_writes and external_calls. It does not clarify units (seconds vs. something else, byte units) or how the values combine, keeping it below 5.

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 verb and resource ('Посчитать цену по фактическому расходу') and enumerates the consumption dimensions being priced. It is clearly distinct from the utility-style siblings (check_skill, suite_status, trust_report, verify_work), but it never explicitly contrasts itself with them, 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 trailing clause '— вместо прайсовой таблицы' hints at when to prefer this tool (consumption-based instead of a static price table), which is implied usage rather than an explicit when/when-not rule. No prerequisites, no named alternative tool, no statement of when this should not be called.

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 behavioral burden. The word 'live' usefully signals a real-time (non-cached) snapshot, which is genuine behavioral context, but it says nothing about permissions, rate limits, or freshness guarantees for what is presumably a monitoring call.

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

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

A single efficient sentence with the resource and its scope front-loaded and no filler. It is terse to the point of cryptic for readers unfamiliar with the layer names, 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?

With an output schema present, return values need not be described, and with zero parameters the call surface is trivial. However, the absence of any usage guidance or annotation leaves a monitoring tool slightly under-specified for an agent deciding when to invoke 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?

The tool takes zero parameters, so there is no parameter semantics to document. Baseline for a param-free tool is 4.

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 resource and scope: the live state of the Suite layers, and enumerates them (attest, agentpay, drift, skilllint). An agent knows this is a read/status tool rather than a verification or quoting tool. It does not explicitly contrast with siblings, keeping it just under 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?

No when-to-use context, no preconditions, and no mention of alternatives among the siblings (check_skill, quote_cost, trust_report, verify_work). The agent must infer usage purely from the name and one-line 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?

No annotations are provided, so the description carries the full behavioral burden. It says the tool aggregates a verification, a cost check, and a mandate/drift check, but never states whether it is read-only, whether invoking it triggers the underlying paid cost check ('цена по факту'), what permissions are needed, or whether it has side effects. The mention of cost is a hint but not a disclosure.

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 that front-loads the core purpose and then enumerates the components. No filler or redundancy, though the parenthetical codenames add ambiguity without adding clarity.

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

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

An output schema exists, so return values need not be described. However, with zero annotation coverage, zero schema description coverage, and an unexplained 'schema' parameter, the description is insufficient for correct invocation; it also never clarifies how this composite relates to calling the three sibling checks individually.

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 the description must compensate. It only implies the meaning of 'artifact' via 'по артефакту агента'; the second parameter 'schema' (string, default '') is left completely unexplained in both schema and description, and no format or syntax is given for the artifact identifier.

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 deliverable (a consolidated verdict on an agent artifact) and enumerates the three constituent checks it rolls up. It distinguishes itself as the aggregate counterpart to the individual checks, though it refers to them by internal codenames ('attest', 'agentpay', 'drift') that do not match the actual sibling names (verify_work, quote_cost), which weakens the routing signal slightly.

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 'use this when you want the combined verdict instead of running each check separately.' There is no explicit when-to-use statement, no guidance on choosing between this tool and the sibling checks, and no prerequisites or exclusions.

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 add real behavioural information — the four validation layers and the fact that it emits an 'attest' verdict — but says nothing about read-only vs mutating behaviour, required permissions, side effects, or cost/latency for what is clearly a gate-keeping check.

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, purpose front-loaded, with the parenthetical grouping the validation layers efficiently. Slightly dense label soup ('пустота', 'полномочия') but no wasted words.

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 output schema covers the return verdict, so that need not be restated, but with no annotations and 0% parameter coverage the definition still leaves an agent without the permission/format/alternative details needed to invoke it confidently.

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% for both parameters, so the description must compensate and largely does not. The mention of 'схема' as a validation layer is only an indirect hint that the optional `schema` parameter exists; the required `artifact` parameter and its expected format (text? JSON? path?) are never explained.

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 verb (проверить / verify) and resource (артефакт агента) and enumerates the four checked layers (схема, пустота, provenance, полномочия), which is more than a tautology. It does not, however, contrast itself with likely-overlapping siblings such as trust_report or check_skill.

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 when-to-use, when-not-to-use, or alternative-tool guidance appears anywhere. An agent has to guess whether an artifact should be routed here or to trust_report/check_skill.

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