Server Quality Checklist

Tool Scores

• a2a_cancel_taskB
  3.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the full behavioral burden. It does disclose that cancellation returns a final state, which is useful, but it omits side effects, idempotency, error behavior, or whether cancellation is irreversible.

  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, front-loaded sentence that states the core operation and the return value without any filler. Every word earns its place.

  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?

  For a state-changing tool with no annotations and no output schema, this description is too thin. Missing details include parameter semantics, handling of non-running tasks, failure modes, and any irreversible consequences, leaving the agent to guess important call behavior.

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

  Parameters1/5

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

  Schema description coverage is 0%, and the description adds no meaning to the 'agent' or 'task_id' parameters beyond their names. Neither the schema nor the description explains what values these accept or how they relate to the cancellation operation.

  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 uses a specific verb ('cancel') and a specific resource ('A2A task'), and clarifies that it returns the task's final state. This clearly distinguishes it from sibling tools like a2a_get_task or a2a_send_message, even without naming 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 this tool is for active/running tasks, giving reasonable contextual usage. However, it does not explicitly state when not to use it, mention alternatives, or explain what to do if the task is already completed.

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

• a2a_add_agentA
  3.5/5.0
  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 and it does meaningful work: it discloses that the agent card is fetched first, unreachable URLs are rejected instead of saved, and persist=true writes to a shared registry file. It does not cover every edge case, but it provides substantial insight into the tool's behavior.

  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 three short, front-loaded sentences with no filler. The core action comes first, and the following sentences provide useful behavioral details without repeating the schema or wasting words.

  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?

  The description adequately covers the main registration flow and persistence behavior, which is enough for a basic call. But it omits important context such as the purpose of headers, what the tool returns after successful registration, and the exact behavior when persist is false, leaving it short of fully complete.

  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 for missing parameter explanations. It adds real meaning for 'url' (base URL) and 'persist' (shared registry file), but it leaves 'name' and especially 'headers' entirely unexplained, and does not clarify what persist=false means for session lifetime.

  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 first sentence names a concrete action ('Register') and a specific resource ('a new A2A agent'), and adds the mechanism ('by its base URL'). This makes the tool's purpose immediately clear and it is obviously distinct from sibling tools like list, send, get, and cancel, though it does not explicitly name those 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 implies when to use the tool through 'Register a new A2A agent,' and it gives some context about persistence across sessions. However, it never explicitly contrasts this tool with alternatives or states when not to use it, so the agent has to infer the usage boundary.

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

• a2a_get_taskA
  3.5/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses that the tool returns state and output, and 'get' implies a read-only operation. However, it does not mention error behavior for unknown task IDs, whether the call is idempotent, or whether it affects task execution in any way.

  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 a single, front-loaded sentence with no fluff. It efficiently communicates the tool's purpose and the key precondition that the task must already exist.

  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?

  With no annotations, no output schema, and zero parameter descriptions, the tool description is too sparse. An agent cannot reliably know what value 'agent' expects, what the returned state/output structure looks like, or what happens when a task does not exist.

  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. The task_id parameter is reasonably inferable from the tool purpose, but 'agent' is ambiguous: it is not explained as an identifier, name, or what agent list it refers to. The description adds no parameter-level meaning.

  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 states a specific verb ('Get') and a specific resource ('current state and output of a previously started A2A task'). It is clearly distinguishable from siblings like a2a_send_message, a2a_cancel_task, a2a_list_agents, and a2a_add_agent, none of which retrieve task state.

  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 phrase 'previously started' implies this should be used to poll or inspect tasks that were already kicked off, which gives a minimal context. However, it provides no explicit guidance about when to choose this over sibling tools, when not to use it, or whether it is intended for polling workflows.

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

• a2a_list_agentsA
  4/5.0
  Behavior3/5

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

  No annotations exist, so the description carries the burden. It usefully discloses caching behavior and the effect of refresh, but it does not state that the operation is read-only, describe the return structure, or mention any potential side effects or prerequisites. Some relevant behavior remains implicit.

  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?

  Two concise sentences: the first states the tool's purpose and result scope; the second explains the only parameter. No filler or duplication of the schema.

  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 simple, single optional-parameter list operation, this description is largely complete. It identifies what the result includes, notes the caching behavior, and explains the parameter. A fully explicit return-format statement would be nice, but it is not essential for correct invocation.

  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 description coverage is 0%, so the description must compensate. It does by explaining that refresh=true re-fetches cached agent cards. It stops short of explaining the exact behavior when refresh is false (e.g., serving from cache), but the meaning is strongly implied.

  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 states a specific action ('List'), a clear resource ('configured A2A agents'), and the relevant output facets ('skills and reachability'). It is immediately distinguishable from its siblings, which send messages or manage tasks.

  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 refresh guidance is clear operational context ('Set refresh=true to re-fetch agent cards that were previously cached'). However, there is no explicit statement about when to prefer this tool over alternatives such as a2a_send_message or a2a_get_task; the distinction is only implied by the name.

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

• a2a_send_messageA
  4.1/5.0
  Behavior4/5

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

  With no annotations available, the description carries the full behavioral burden. It discloses the asynchronous/non-blocking timeout behavior, the done=false + task_id polling contract, and the nuance that the provider field may be ignored by non-local agents. It does not mention auth, error cases, or side effects, but it covers the most important behavioral traits for correct invocation.

  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 front-loaded with the core purpose and then supplies only high-value operational details: provider selection, task continuation, and polling behavior. Every sentence earns its place, and the length is appropriate for the complexity.

  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?

  The description is useful for a complex async tool, but there is no output schema and no annotations, so the description must explain the return contract. It partially does by mentioning 'reply,' 'done=false,' and 'task_id,' yet it never describes the full response shape, error behavior, or the purpose of context_id. An agent could still be uncertain about the exact payload format.

  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 adds meaning for provider, task_id, and timeout_s, and the required agent and message parameters are inferable from 'send a message to an A2A agent.' However, context_id is never explained, leaving one of six parameters semantically undocumented.

  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 opens with a specific verb and resource: 'Send a message to an A2A agent and return its reply.' This clearly distinguishes the tool from its siblings (a2a_list_agents, a2a_get_task, a2a_cancel_task, a2a_add_agent), all of which serve different operations.

  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 clear context for when to use it: sending messages, continuing existing tasks via task_id, responding to state="input_required", and handling non-blocking timeouts. It does not explicitly name a2a_get_task as the polling alternative, but strongly implies the polling workflow by mentioning 'to poll rather than blocking.'

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