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

No annotations are provided, so the description carries the burden. It implies a read-only lookup (a definition, not an execution) and discloses what the payload contains, but says nothing about permissions, caching, or lookup failure behavior. Output schema covers the return shape, so this is the acceptable minimum.

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 what the tool returns first and the consult trigger last. No filler, though the enumeration is slightly dense.

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 one documented parameter and an existing output schema, the description needs only to convey purpose and the consult trigger, which it does. An agent has enough to call it correctly; only clearer routing against query_metric 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% with a single well-named "metric" parameter ("Nome canônico da métrica"). The description adds no format or canonicalization guidance 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?

Starts with a specific verb+resource ("Definição completa de uma métrica") and enumerates the payload it delivers: expression, grain, dimensions, allowed filters, and usage notes. This clearly separates it from query_metric and list_metrics, though no sibling is named 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?

"Consulte antes de montar um recorte incomum" gives one loosely-stated situation to reach for this tool, but the conditions are vague (what counts as "incomum") and no alternative (e.g. query_metric) is referenced for the common case. The "quando usar/quando NÃO usar" phrasing describes output content, not tool-selection 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 behavioral burden. It implies a read-only traversal but never states the operation is non-mutating, nor what happens for an unknown or non-existent metric, nor any permission requirements. Behavior beyond the conceptual output shape is largely undisclosed.

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, both earning their place: the first defines the resource and its boundary, the second states the use case. Purpose is front-loaded with zero filler.

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-parameter read tool with an output schema (so return values need no prose) and full schema coverage, the description covers purpose and trigger adequately. Only the silence on failure/edge behavior with no annotations keeps it from being fully 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% for the single `metric` parameter, which already documents it as the canonical metric name. The description adds no naming convention, format, or lookup guidance beyond that, 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?

Names a specific resource and scope: the chain of dbt models producing a metric, from source to mart. This is clearly distinct from query_metric (returns numbers) and describe_metric (definition), though it never names those siblings 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?

"Use para responder de onde vem o número" gives a clear, concrete usage context — answering provenance questions about a metric. No exclusions or named alternatives are offered, but the trigger condition 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?

No annotations are provided, so the description carries the full burden. It is a zero-parameter list operation and 'Lista' implies a safe read, but the description never states that it is read-only or non-mutating, nor does it mention any auth or result-size behavior. It does add useful content context by naming the fields returned.

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, zero waste, with the purpose front-loaded before the 'start here' guidance. Every clause earns its place.

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-param discovery tool with an output schema already present, the description is nearly complete; it need not explain return values. A small gap is the absence of any note about ordering, volume, or whether results are paginated, but nothing critical to correct invocation 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?

The tool takes zero parameters, so there is nothing to disambiguate and the baseline is 4. The description correctly refrains from inventing parameters and instead describes the output shape.

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 and resource ('Lista todas as métricas do contrato semântico') and enumerates what each entry carries (rótulo, descrição de negócio, dimensões aplicáveis). It does not explicitly name the siblings (describe_metric, query_metric), but its 'start here / complete vocabulary' framing does implicitly separate it as the discovery entry point.

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?

'Comece por aqui' gives clear positive guidance on when to reach for this tool first, positioning it as the vocabulary-discovery step before drilling into a specific metric. It stops short of naming the alternative siblings or stating when not to use it.

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 present, the description carries the behavioral burden and does disclose key traits: the SQL rejection rule, the contract-only naming constraint, and the shape of the result (rows, metric definition, compiled SQL for auditing). It omits permission/auth or rate-limit behavior, but the input/output contract is well surfaced.

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 action and immediately followed by the critical constraint and the return contract. No filler; every sentence earns its place.

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 re-explained, yet the description helpfully names them. It conveys the core constraint (no SQL, contract names only) for a 4-parameter tool. Minor gap: no guidance on how to obtain valid metric/dimension/filter field names within the contract.

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 metric, filters, dimensions and limit with defaults and constraints (maxItems 3, max 10000). The description only reinforces the 'contract-declared names only' rule, adding no parameter-level detail beyond the schema 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?

States a specific verb+resource ('Executa uma métrica com recortes e filtros opcionais') and clearly separates this tool from siblings like list_metrics/describe_metric by emphasizing execution with dimensions/filters rather than listing or describing metadata.

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?

Gives a clear negative constraint ('NÃO aceita SQL: informe apenas nomes declarados no contrato'), which is essential guidance for invocation. It stops short of explicitly routing to siblings (e.g. use describe_metric first to discover names), so it is strong context but not full when/when-not coverage.

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