Server Quality Checklist

Tool Scores

• recording_statusA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full behavioral burden and covers the key ground: all three possible states, what 'stale' means, and how the stale file will be removed on the next start_recording. It does not explicitly promise that the call is side-effect-free, but the verb 'Informa' implies a read-only status check.

  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 a one-line purpose and then gives a compact Returns block covering every possible outcome. There is no filler or redundancy, and every sentence adds meaningful information.

  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 no-parameter tool with no annotations and no output schema, this description is complete: it defines each return state, the meaning of 'stale', and the recovery behavior. An agent can confidently invoke it and interpret the result correctly.

  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 the schema already documents this completely with 0 properties. The description correctly avoids inventing parameter-level detail, which matches the baseline for a 0-parameter tool.

  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 states the tool's purpose and domain ('Informa se há uma gravação em andamento'), and the Returns section enumerates exactly what it reports. It is clear enough to distinguish from the start/stop siblings, but it never explicitly names the 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?

  Usage is implied rather than stated: this is clearly the state-checking tool alongside start_recording and stop_recording, and it mentions that start_recording handles stale state. However, it gives no explicit 'use this when...' or 'do not use this to start/stop' guidance.

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

• stop_recordingA
  4.2/5.0
  Behavior4/5

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

  The description clearly states that the method blocks until the WebM file is finalized, including duration and index metadata, and that the timeout parameter controls waiting. It also discloses the return value with path, size, and duration. With no annotations provided, this is strong behavioral disclosure, though timeout failure behavior is not described.

  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 short, structured, and front-loaded with the main behavior before diving into parameter and return details. Every sentence adds relevant information with no redundancy or filler.

  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 is simple: one optional parameter and no output or input schema beyond the timeout. The description explains what the tool does, how it behaves, what the timeout means, and what the return value contains. The only missing detail is what happens when the timeout expires—whether it raises an error, returns partial data, or still returns a summary. This is a meaningful but minor gap in an otherwise complete description.

  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 only provides the parameter name and default value, and schema description coverage is 0%. The description compensates by explaining that timeout is the number of seconds to wait for the auxiliary process to close the file. This is enough for an agent to know how to set it appropriately.

  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?

  States a specific action (end current recording), a specific resource (the recording in progress), and key behavioral constraints (waits for the WebM to be complete). The function is clearly distinct from its siblings start_recording and recording_status.

  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 clearly implies this is the operation to stop a recording after start_recording has begun, but it does not explicitly mention alternatives or conditions for when recording_status might be preferable. An agent can infer the correct use case, though the guidance is not explicit.

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

• start_recordingA
  4.8/5.0
  Behavior5/5

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

  There are no annotations, so the description carries the full behavioral disclosure burden. It does so thoroughly by saying the call returns immediately, recording continues in the background, only one recording can exist, and the return includes the file path and the PID of the helper process keeping it alive.

  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 well structured and front-loaded: it opens with the core behavior, then provides a compact Args section and a Returns note. Every sentence contributes meaningful information with no filler or 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 an asynchronous operation with no annotations or output schema, the description is highly complete. It explains when to call it, how it runs, when it stops, what parameters matter, and what the return value contains. The only omitted detail is error behavior when a recording already exists, but the single-recording constraint makes that outcome interpretable.

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

  Parameters5/5

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

  Schema description coverage is 0%, but the description compensates completely: output is explained with .webm, default timestamped location, and the '%' restriction; framerate is given units; draw_cursor behavior is described; and area is defined as [x, y, width, height] pixels with a full-screen default.

  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 first sentence clearly states the operation: it starts a screen recording and returns immediately. It also frames the recording's lifecycle relative to stop_recording, making it distinct from the sibling tools stop_recording and recording_status.

  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 strong lifecycle guidance: the recording continues in the background until stop_recording is called, and only one recording can exist at a time. It does not explicitly mention when to prefer recording_status over start_recording, so it falls just short of full alternative-routing guidance.

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