Server Quality Checklist

Tool Scores

• contextB
  3/5.0
  Behavior2/5

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

  There are no annotations provided, so the description carries full responsibility for behavioral disclosure. It does state 'Somente leitura' (read-only), which covers the safety profile, but provides no detail about what the tool actually returns, whether it searches the whole codebase or specific docs, what scope its knowledge covers, or any limitations. Given zero annotation coverage, this is thin.

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

  Conciseness3/5

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

  The description is brief and front-loaded, stating purpose and read-only nature in two concise clauses. However, it includes some filler phrasing ('Consulta livre ao conhecimento do projeto') and could be tightened. It's reasonably efficient but not maximally dense with useful information.

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

  Completeness2/5

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

  This is a knowledge-consultation tool with an output schema but no annotations. With zero parameter documentation and minimal behavioral disclosure, the description leaves significant gaps: what kind of knowledge domain, what volume/format of output, whether it's code-aware or documentation-aware, and how it differs from 'search'. For a knowledge-query tool, the description should provide more context about its answer scope and nature.

  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?

  With 0% schema description coverage and only one 'query' parameter, the description offers the example 'o que sabemos sobre autenticacao?' which implies the query is a natural-language question. However, it doesn't specify the expected format, language, or any constraints on the query beyond the example. The single simple parameter partially compensates, but the description adds minimal formal guidance about it.

  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 clear purpose: free consultation of project knowledge, distinguished from task-initiation queries via the example 'o que sabemos sobre autenticacao?'. It clearly states read-only behavior. It distinguishes from siblings implicitly by noting this is for non-task queries, though it doesn't name specific sibling alternatives.

  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 gives an explicit usage context ('quando a pergunta nao e o inicio de uma tarefa') and provides a concrete example query. However, it doesn't explicitly say when NOT to use it or name alternative tools, though the sibling context (search, start_task) implies an alternative. The guidance is useful but not exhaustive.

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

• searchB
  3.1/5.0
  Behavior3/5

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

  No annotations are provided, so description carries the burden. It usefully states 'Somente leitura' (read-only), which is valuable behavioral context. However, it doesn't describe return behavior, pagination, result format, or what types are available for filtering, despite having an output schema. The read-only disclosure is helpful but the description is thin on behavioral detail.

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

  Conciseness4/5

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

  The description is a single efficient sentence that conveys purpose and read-only nature. No wasted words. Though terse, it earns its brevity by being direct. It could benefit from more structure but is appropriately compact.

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

  Completeness2/5

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

  The tool is a search/filter tool with an output schema and 3 parameters, yet the description covers none of the parameters, doesn't explain the types enum behavior, and doesn't describe filtering capabilities. Sibling tools (remember, context) overlap in domain, making usage ambiguity a real concern. With 0% schema coverage and no annotation support, the description is insufficient for confident invocation, especially regarding the 'types' parameter.

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

  Parameters2/5

  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, but it adds zero parameter information. It doesn't explain what 'query' should contain, what 'types' values are valid, or how 'limit' affects results. All three parameters are undocumented in both description and schema properties beyond their titles, leaving the agent guessing about format and semantics.

  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 clearly states the purpose: searching the project's registered knowledge (decisions, entities, preferences, conventions, technologies). The verb 'Procura' (search) plus resource scope is specific and distinguishes it from sibling tools like remember (write) and context. However, it lacks explicit differentiation from siblings beyond the domain mention.

  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 'Somente leitura' (read-only) indicates it's a read operation, which helps distinguish from remember (write). The domain is described (knowledge base of the project). However, it doesn't explicitly state when to use vs alternatives, and siblings like context could plausibly overlap in purpose without clear guidance on which to choose.

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

• finish_taskA
  3.8/5.0
  Behavior3/5

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

  The description explicitly states the tool does NOT write anything ('NAO grava nada') and requires user approval before calling `remember`, which is important behavioral transparency. However, no annotations are provided, so the description carries the full burden; it does not mention what the return/output looks like beyond the change_set being returned, and doesn't clarify side effects of the analysis itself.

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

  Conciseness4/5

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

  Three sentences, dense with information, no waste. The description packs purpose, workflow, non-persistence behavior, and the approval gate into a compact block. Slightly long but every sentence earns its place; the flow is clearly presented.

  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 tool with one string parameter and a rich workflow (analyze, suggest, get approval, call remember), the description covers the key behavioral elements. The output schema exists, so return format needn't be detailed. It could mention error cases or what happens if analysis yields nothing, but overall it's fairly complete for this complexity.

  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?

  Schema coverage is 0%, so the description fully carries the burden for parameter meaning. It explains that `summary` should be a summary of what was done and decided, which adds meaningful context. With only one parameter and this explanation, the guidance is adequate and adds value beyond the bare schema.

  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 clearly states the tool finishes a task by passing a summary of what was done and decided. It names the specific verb (finish) and resource (task). It distinguishes from siblings by explaining this is the task-completion step, separate from remember (persisting knowledge) and search/context.

  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 provides clear guidance on when to call it (when finishing a task) and the workflow: it analyzes the summary, suggests what should become permanent knowledge, doesn't save anything, and only calls `remember` if the user approves the change_set. It names the alternative (`remember`) and the conditional flow, though it doesn't explicitly say when NOT to use it beyond the non-writing behavior.

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

• rememberA
  3.9/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It explicitly discloses the key behavioral trait: 'Escreve em disco: confirme com o usuario antes' (writes to disk, confirm with the user first). This is a side-effect disclosure that is valuable. However, it doesn't describe return values or what confirmation flow looks like in detail, but the disk-write disclosure is the critical one.

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

  Conciseness4/5

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

  The description is a single compact paragraph of three sentences. It's front-loaded with the core purpose, then usage modes, then the critical side-effect warning. No filler or repetition. Slightly dense but efficient.

  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?

  Despite 0% schema coverage and no annotations, the description covers the essential aspects: purpose, two usage modes, and the write-to-disk side effect. It has an output schema, so return value explanation isn't strictly needed. For a tool with 4 parameters and no annotations, this is reasonably complete, though it could elaborate on confirmation expectations.

  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?

  Schema description coverage is 0%, so the description must compensate. It groups parameters into two usage modes (change_set vs type/title/content) which adds semantic meaning beyond the bare schema. However, it doesn't explain each parameter's type requirements or format details, leaving the agent to infer specifics. The mode-grouping is helpful but not exhaustive.

  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 clearly states what the tool does: 'Grava conhecimento na base do projeto' (records knowledge in the project base). It identifies the resource (knowledge base) and the action (record/save). It distinguishes the two usage modes (change_set with an approved finish_task suggestion, or standalone type/title/content) which helps differentiate from siblings.

  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 provides clear usage context: use with change_set for applying an approved finish_task suggestion, or with type/title/content for standalone records. It names the specific sibling tool (finish_task) and describes when to use each mode, though it doesn't explicitly say when NOT to use it or name direct alternatives for recording knowledge.

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

• start_taskA
  3.9/5.0
  Behavior3/5

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

  There are no annotations provided, so the description carries the full burden of behavioral disclosure. It explicitly states 'Somente leitura' (read-only), which is valuable behavioral information. However, it doesn't disclose what happens when no relevant knowledge exists, potential failure modes, or whether it modifies state in any way beyond the read-only claim.

  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 compact—three sentences in Portuguese—and front-loaded with the most critical instruction (call before starting any task). Every sentence adds value: the timing instruction, the output description, and the read-only note. No wasted words.

  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?

  The tool has a single required parameter and an output schema present, which lowers the burden on the description for explaining return values. The description covers the tool's core behavior adequately for its simplicity. However, given 0% schema coverage, it would benefit from elaborating on what the 'task_description' parameter should contain, and the relationship to sibling tools like 'remember' and 'context' is not clarified.

  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?

  Schema coverage is 0%, so the description must compensate for the sole parameter. While the description explains the overall tool behavior well, it doesn't specifically describe what the 'task_description' parameter should contain (e.g., format, level of detail, whether it's a free-form description or a specific format). With only one parameter and 0% schema coverage, the description carries the burden and only partially addresses the parameter's intended usage.

  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 clearly states the tool's purpose: 'Chame ANTES de comecar qualquer tarefa neste projeto' (call BEFORE starting any task in this project), and explains what it does—returns accumulated knowledge relevant to the task including project rules, decisions, preferences, and conventions. While clear and specific, it doesn't explicitly distinguish itself from the sibling tools like 'context', 'search', or 'remember', which could overlap in function.

  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 gives explicit usage context: it should be called BEFORE starting any task. 'Chame ANTES de comecar qualquer tarefa' is a clear temporal guideline. However, it doesn't explicitly state when NOT to use this tool versus alternatives like 'search' or 'context', nor does it name specific sibling alternatives for exclusion.

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