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

With no annotations provided, the description carries the full burden. The verb 'List' clearly implies a non-destructive read operation, and the description details the output content (which files, by whom, when they expire). This is sufficient for a 0-parameter read-only tool.

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?

The description is two sentences with no redundant information. The first sentence conveys the primary action, and the second provides complementary details. All words are purposeful and front-loaded.

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 simple 0-parameter list tool with no output schema, the description adequately covers what the tool does and what it returns (fields: files, lock holder, expiration). It lacks any mention of prerequisites or edge cases, but given the low complexity, this is nearly 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?

The tool has zero parameters, and the schema coverage is effectively 100% (empty properties). According to the rubric, 0 parameters warrants a baseline of 4. The description adds no parameter semantics, but none are needed.

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?

The description clearly states the tool's function with a specific verb ('List') and resource ('all active file locks'). It also specifies what information is shown (locked files, by whom, expiration), which distinguishes it from siblings like lock_files and release_files.

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?

The description implies usage context (when you want to see file locks) but does not explicitly mention alternatives or exclusions. No reference to sibling tools like lock_files or release_files, so the when-to-use guidance is only implicit.

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, the description carries the full burden. It clearly indicates a read-only status check, but it does not disclose behavior when not connected, potential errors, or return format specifics. This is adequate but not rich.

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 conveys the entire purpose with no wasted words. It is highly concise and well-structured.

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 simple no-parameter status tool, the description sufficiently covers the core behavior. However, the lack of an output schema means the return value is not specified, leaving a minor gap for an agent needing to interpret the result.

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 has zero parameters, making schema coverage trivially 100%. The description need not describe parameters, and the baseline of 4 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?

The description uses the specific verb 'Check' and identifies the resource ('coordination server you are currently connected to'), making its purpose clear and distinguishing it from the sibling tool 'connect_remote' which establishes a connection.

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?

No explicit guidance is given on when to use this tool versus alternatives. The purpose implies it is for checking current connection status, but it does not state exclusions or mention related tools like 'connect_remote'.

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, the description carries the full burden. It adds useful behavioral guidance by pointing to the token's location and instructing the agent to ask the user for missing values, but it does not describe post-connection behavior, failure handling, or whether the connection persists.

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 concise sentences each serve a purpose: stating the action, providing usage context, and instructing the agent on obtaining required values. No wasted or redundant content.

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 simple two-parameter connect tool, the description covers purpose, usage context, parameter sourcing, and user interaction. Missing details about connection lifecycle or failure modes are acceptable given the simplicity, but there is some room for improvement.

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 schema already describes both parameters (100% coverage), but the description adds extra meaning by detailing where the token is found (acdp-socket-server/config.json) and reinforcing the user-instruction aspect, which goes beyond the basic schema descriptions.

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?

The description clearly states the action ('Connect') and the resource ('remote ACDP coordination server'), and differentiates from siblings like start_local and connection_status by specifying cross-machine coordination.

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?

It explicitly says 'Use this when you need to coordinate with agents running on a different computer,' providing clear context for when to use it. It does not explicitly name alternative tools or exclusions, but the context is sufficient.

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 exist, so the description carries the full burden. It discloses the main behavior (listing agents and their status) but does not add context such as read-only nature, potential network dependencies, or response format. The word 'List' implies a read operation, but there is no explicit mention of safety or side effects.

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?

The description is a single, front-loaded sentence with no wasted words. It states the action and the key information returned.

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?

Given the tool's simplicity and lack of output schema, the description sufficiently explains what the tool returns: all agents and their connection status. It does not explicitly describe the data structure, but for a list operation this is adequate.

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 has zero parameters, and schema coverage is 100%, so the baseline is 4. The description adds no parameter details because none are needed.

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?

The description clearly states the action (List) and the resource (all agents registered on the coordination server), plus the additional detail of connection status. This distinguishes it from siblings like connection_status, which likely focuses on current server connection rather than all agents.

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?

The description implies when to use it (when you need an overview of agents and their status), but it does not provide explicit guidance on alternatives or exclusions. It does not mention that connection_status might be used for a single connection check, so usage context is inferred rather than explicit.

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, the description carries the full burden. It discloses that other agents see files as unavailable and that the operation fails if any file is already locked. This provides meaningful behavioral context, though it omits details like lock duration or release mechanism.

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 concise sentences, front-loaded with the action and result. Every word earns its place with no redundancy or 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 straightforward locking tool, the description covers the core purpose, effect on other agents, and failure mode. It doesn't need to explain return values (no output schema), and the sibling tools imply the broader workflow. Slight gaps like lock persistence are acceptable.

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 schema already describes both parameters (files and reason) with 100% coverage, so the description doesn't need to add parameter details. It does implicitly tie the 'files' parameter to the locking behavior, but adds no extra semantic enrichment beyond the schema.

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?

The description clearly states the tool locks files before modification, with a specific verb and resource. It also distinguishes itself by noting the effect on other agents and the failure condition when files are already locked, setting it apart from siblings like release_files and check_locks.

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?

The description indicates when to use the tool ('before modifying them'), providing clear context. It doesn't explicitly contrast with alternatives like check_locks or release_files, but the usage timing is clear, so only a slight gap in exclusion 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?

With no annotations, the description carries the full burden. It discloses the broadcast effect (all other agents notified), the synchronization trigger, and a critical side effect (auto-releasing locks). It does not mention failure modes or prerequisites beyond committing, but the key behaviors are covered.

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 sentences, 37 words, with the primary action stated first and the side effect in the second. Every sentence earns its place with no filler or redundant phrasing.

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 simple two-parameter tool with no output schema and no annotations, the description covers the core behavior (notification) and a key side effect (lock release). It lacks explicit discussion of the optional 'message' parameter, but the schema covers that, and the prerequisite is mentioned.

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 coverage is 100%, and the description adds no additional details about the 'files' or 'message' parameters. It only refers to 'these files' implicitly, so it relies entirely on the schema for parameter semantics.

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?

The description clearly states the tool notifies other agents about updated files after committing and distinguishes it from siblings by noting it also auto-releases locks. The verb 'notify' and resource 'other agents' make the purpose specific and unambiguous.

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?

It provides a clear temporal context ('After committing changes') and explains the effect on other agents. However, it does not explicitly name alternatives like release_files or state when not to use this tool, so it lacks explicit exclusion conditions.

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 discloses that the operation releases the caller's own locks ("your locks") and is tied to the concept of exclusive access, but it does not mention error behavior, idempotency, or side effects. This is minimal but present.

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?

The description is two sentences with no filler, front-loading the core action and following with a usage condition. Every word 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 simple tool with one fully-described parameter, no output schema, and no annotations, the description adequately covers purpose and usage. It does not address return values or failure modes, but given the simplicity and lack of complex behavior, this is acceptable.

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 input schema fully describes the only parameter (files) as "Array of file paths to release", and the description's phrase "your locks on files" aligns with this. The description adds no additional meaning beyond the schema, so it earns the baseline score.

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?

The description clearly states the tool's action with a specific verb ('release') and resource ('your locks on files'), which directly distinguishes it from sibling tools like lock_files and check_locks. The purpose is unambiguous and specific.

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 this when you no longer need exclusive access" provides a clear condition for when to invoke the tool. It implies the alternative (lock_files) is for when exclusive access is still needed, though it does not explicitly name alternatives or exclusions.

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, the description carries the full burden. It discloses the approval workflow (auto vs manual) and the dependency on holding a lock, which is valuable. It does not mention failure modes or response format, but core behavioral traits are covered.

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 sentences with the main purpose front-loaded and the second sentence elaborating approval conditions. No wasted words or redundant information.

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?

The tool is simple with only 2 parameters and no output schema. The description covers the core approval workflow but does not explain what happens after approval or rejection, nor any timeouts or response format. This is adequate for a basic request tool but leaves some ambiguity.

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 schema provides 100% coverage of both parameters with descriptions for 'files' and 'summary'. The description adds no additional parameter semantics beyond what the schema already states, so baseline 3 is appropriate.

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?

The description clearly states the tool's action: 'Request permission to commit changes to files.' This is a specific verb+resource pairing that is distinct from sibling tools like lock_files and release_files, which deal with locking and releasing rather than committing.

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?

It provides clear context for when the tool is used by explaining the auto-approval condition (holding the lock and non-manual path) versus waiting for owner approval. However, it does not explicitly mention alternative tools for different workflows, so it lacks explicit exclusions.

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 discloses key behaviors: becoming the owner and generating a token that others use to connect via IP. However, it omits lifecycle details such as whether the server runs in the background, how to stop it, or what the output (e.g., token and IP) looks like. This is moderately transparent but incomplete.

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?

The description is three sentences, front-loaded with the primary action ('Start a local ACDP coordination server'). Every sentence adds value: what it does, who becomes owner, how others connect, and when to use it. No wasted words.

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 tool with no output schema and no annotations, the description explains the core behavior but does not clarify how the IP/token are returned (via output, logs, etc.) or whether the process blocks. This leaves post-invocation expectations vague, which is a significant gap for a state-changing server-start tool.

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 input schema has zero parameters, and the description adds no parameter-specific details, which is appropriate. With no parameters to document, the baseline of 4 is warranted. The description does not need to compensate for missing schema coverage.

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?

The description opens with a specific verb and resource: 'Start a local ACDP coordination server.' It clearly differentiates from siblings like connect_remote by stating 'You become the owner' and that other agents connect to you. This is not a tautology and uniquely identifies the action.

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?

The description explicitly provides a usage condition: 'Use this when YOU are hosting the coordination.' This is clear context, though it does not explicitly name the alternative (e.g., connect_remote) or include a when-not-to-use clause. The condition is sufficient to guide the agent.

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