Server Quality Checklist

Tool Scores

• taxi_authenticateA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It discloses a key behavioral trait: the token is not revealed, only success/failure is returned. It also implies a side-effect-free authentication check. However, it does not disclose failure behavior, rate limits, or what happens on invalid credentials. The description adds some value but leaves gaps.

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

  Conciseness5/5

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

  Three short sentences, each carrying distinct information: what it does, what it returns, and what it requires. No fluff, front-loaded with the action.

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

  Completeness3/5

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

  For a zero-parameter authentication tool with no output schema, the description covers the main points: action, credential source, and return behavior. However, it lacks details on error cases (e.g., invalid credentials, network failure) and whether repeated calls are safe. Given the simplicity, it is adequate but not fully complete.

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

  Parameters4/5

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

  The input schema has zero parameters, so there is nothing for the description to add about parameters. The description explains that credentials come from environment variables (TAXI_LOGIN/TAXI_PASSWORD), which is useful context beyond the empty schema. Baseline 4 for zero-param tools is appropriate.

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

  Purpose4/5

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

  The description states a specific verb ('Выполняет вход' – performs login) and resource (TAXI_LOGIN/TAXI_PASSWORD auth chain), and clarifies that it returns only success/failure, not the token. It is distinguishable from siblings like taxi_status or taxi_reference_list, though it doesn't explicitly name them.

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

  Usage Guidelines3/5

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

  The description implies when to use it: when credentials are available and authentication is needed. It states a requirement ('Требует учётных данных') but does not explicitly contrast with alternatives or say when not to use it. Sibling names suggest other tools are for status/reference, so context is somewhat clear but not explicit.

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

• taxi_reference_getA
  4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the behavioral disclosure burden. It explicitly says 'Read-only, без авторизации', which tells the agent the tool has no mutation side effects and needs no authentication token. This is particularly useful with a taxi_authenticate sibling present. It does not mention pagination or output size, but the core read/no-auth traits are clearly declared.

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

  Conciseness5/5

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

  The description consists of two short sentences, the first front-loading the core action and concrete examples, and the second adding the important access/behavioral facts. Every clause earns its place with no filler or redundant restatement of the tool name.

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

  Completeness4/5

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

  For a one-parameter getter with no output schema, the description is nearly complete: it explains what is returned, hints at valid table names, and clarifies read-only/no-auth behavior. It could be slightly richer by explicitly pointing to taxi_reference_list for discovering valid table names, but the schema already supplies that linkage.

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

  Parameters3/5

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

  The input schema already describes the single 'tables' parameter clearly—names from taxi_reference_list—so schema coverage is 100% and the baseline is 3. The description adds concrete examples of table names like car_classes and currencies, which is mildly helpful but does not meaningfully expand the semantics beyond the schema.

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

  Purpose5/5

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

  The description names the exact action and resource: returning full contents of reference tables, and gives concrete examples such as car_classes, currencies, and payment_ways. It is clearly distinct from the sibling list-style tool (taxi_reference_list) and from the unrelated status/authentication tools, so an agent can identify its role immediately.

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

  Usage Guidelines3/5

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

  The description conveys that the tool is for retrieving reference table contents and states that it is read-only, but it does not explicitly explain when to use it versus taxi_reference_list or when not to use it. Table-name discovery is only implied through the schema description, not stated in the usage guidance itself.

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

• taxi_reference_listA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses that the operation is read-only and requires no authorization, which are essential behavioral traits. It also mentions the return includes cache version. It does not cover errors or performance, but for a simple list tool this is adequate.

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

  Conciseness5/5

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

  The description is extremely concise, consisting of two short sentences that state the core function and key behavioral constraints. Every word adds value, and the primary information (what is listed) is front-loaded.

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

  Completeness5/5

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

  Given no output schema and no annotations, the description covers what the tool returns (names, sizes, cache version) and access requirements (read-only, no auth). For a simple list tool, this is complete; an agent can call it without further guidance.

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

  Parameters4/5

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

  The tool has zero parameters, so there is nothing to explain. Per the guidelines, baseline for zero-parameter tools is 4. The description adds operational context but no parameter-specific semantics are needed.

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

  Purpose5/5

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

  The description explicitly states the tool returns names and sizes of all public reference directories under /data/, including cache version. It clearly identifies the resource and function, distinguishing it from siblings like taxi_reference_get which likely fetches a specific table.

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

  Usage Guidelines3/5

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

  The description implies this tool is for listing available reference tables but does not explicitly name alternatives or provide when-to-use versus when-not-to-use guidance. The read-only and no-auth statements hint at safe usage but do not direct selection among siblings.

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

• taxi_statusA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states the operation is read-only, requires no credentials, and enumerates what the response contains. It does not describe failure modes, but for a simple status probe this is adequate.

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

  Conciseness5/5

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

  A single compact sentence front-loads the core action ('checks backend availability') and then lists the returned data and key behavioral traits. Every clause earns its place with no redundancy.

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

  Completeness5/5

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

  For a zero-parameter, no-output-schema status tool, the description is complete: it states the purpose, the behavioral safety profile, the credentials requirement, and the returned fields. Nothing an agent needs to select and invoke it correctly is missing.

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

  Parameters4/5

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

  The tool has zero parameters and 100% schema coverage, so there are no parameter semantics to explain. The description appropriately adds that credentials are not required, which is the only relevant input-related information.

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

  Purpose5/5

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

  The description names a specific verb and resource: it checks backend availability and returns tenant, reference version, and authorization state. This clearly distinguishes it from the sibling reference/authentication tools, whose purposes are different.

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

  Usage Guidelines4/5

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

  The description clearly implies the tool is a lightweight connectivity/status check and explicitly notes it is read-only and requires no credentials, which signals when it is appropriate to call. It does not explicitly contrast with taxi_authenticate, but the context is sufficiently clear.

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