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

With no annotations, the description carries the full burden and does so well: it discloses that in headless mode file changes are only PROPOSED unless CURSOR_ALLOW_YOLO=true, that --force then applies them, that CURSOR_SANDBOX=enabled confines them, and that the result lists changed files plus the model used. It even documents that progress tokens yield a notification per tool call, which is behavior an agent cannot infer from schema or annotations.

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?

Four information-dense sentences with no filler: capability and model scope first, then mode semantics, then the critical headless-safety caveat, then result/progress behavior. Every sentence carries load and the most consequential fact (propose-only vs --force) is placed where it will be read.

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 5-parameter, prompt-driven agent-execution tool with an output schema present, this is complete: execution modes, model sourcing, the propose-vs-apply safety model with its env-var controls, and progress-notification behavior are all covered, and return contents need not be detailed further given the output schema.

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 mode, model, prompt, workspace, and timeout are all already documented in the schema, including the same mode definitions. The description's model-family enumeration and 'run cursor_models for ids' note restate schema content rather than adding syntax or constraints, 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?

States a specific verb and resource ('Execute a prompt using Cursor's AI agent') and immediately scopes it by noting that any model id the installed cursor-agent accepts works, pointing to cursor_models for ids. An agent can distinguish this from cursor_reply, cursor_sessions, and cursor_health without opening any schema.

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 three modes are spelled out with their operational meaning ('agent' = tools/terminal/search, 'plan' = design-focused, 'ask' = read-only), which gives clear when-to-use guidance for mode selection, and cursor_models is named as the source of model ids. It stops short of explicit routing rules against sibling tools like cursor_reply or cursor_sessions, so it is clear context without 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 burden and does disclose the scope of checks performed. However, it never states that the call is non-destructive/read-only, whether it requires credentials to run, or what a failed check looks like. For a harmless diagnostic the risk is low, so the gap is moderate rather than severe.

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 filler, with the action and its scope front-loaded before the usage cue. Nothing is redundant with the tool name.

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 zero-param diagnostic, the description covers what is checked and when to call it. The only missing piece is what the result contains (e.g., per-check pass/fail status), which matters slightly since no output schema exists.

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 for the description to disambiguate; the baseline of 4 applies. No misleading parameter hints are present.

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 (Check) and three concrete resources it inspects: CLI installation, authentication, and server configuration. This is unmistakably a diagnostic tool, cleanly distinguished from the action-oriented siblings (cursor_agent, cursor_reply, cursor_sessions).

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?

"Run this first to verify everything is set up correctly" gives an explicit trigger (setup verification / initial call). It lacks any when-not guidance or named alternatives, but for a zero-param health check the usage context is clear enough.

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 burden. It usefully discloses fallback behavior ('or a known list when it offers none'), implying results may not always reflect the local install, but says nothing about ordering, completeness, auth requirements, or latency.

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 sentences, zero waste, and the primary purpose is front-loaded. The pricing pointer is not filler since pricing is not returned by the tool and users frequently need it.

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 no annotations and no output schema, the description still covers what is returned (model ids), the fallback case, and how to consume the output. Only the exact return shape (e.g., array vs. text, ordering) is left unspecified, which is minor for a zero-arg list 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 tool takes zero parameters, so there is no parameter surface to document and the baseline of 4 applies. The description correctly implies no arguments 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?

States a specific verb and resource ('List the model ids the installed cursor-agent offers') plus the underlying mechanism (its `models` command). An agent can immediately distinguish it from siblings like cursor_agent, which is the tool that consumes these ids.

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 clear downstream context: 'Use an id with cursor_agent's model parameter,' which tells the agent when this tool is needed (before invoking cursor_agent with a model). There is no explicit when-not-to-use or stated alternative, but the routing intent 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 behavioral burden. It discloses the dependency on a prior cursor_agent/session_id, but says nothing about side effects (an agent session can read and modify code), blocking behavior, or what happens on failure/timeout for what is effectively a long-running state-changing call. The timeout semantics live only in the schema, and agent-session side effects are never 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 core action and free of filler. The final sentence overlaps with the schema's session_id description, but it also usefully points at the sibling that produces the ID, so it earns most of 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 no explanation, and all four parameters are documented in the schema. The description covers the action and the entry precondition, leaving only behavioral concerns such as side effects and long-running/blocking execution unaddressed.

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 the model, timeout, session_id and prompt parameters all documented in the schema itself. The description only restates the session_id requirement already covered in the schema and adds no format, default, or interaction detail for model/timeout overrides, 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?

States a specific verb and resource ('Continue an existing Cursor agent session', 'Send a follow-up message') and contrasts implicitly with cursor_agent by emphasizing that the session must already exist. An agent can distinguish it from the session-creating sibling, though the contrast is framed as a prerequisite rather than an explicit sibling comparison.

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?

Clearly establishes the usage context ('the same conversation context') and the precondition ('Requires a session_id from a previous cursor_agent call'), which effectively routes the agent to cursor_agent when no session exists. No explicit when-not or named alternative is stated, so it falls short of a 5.

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 disclosure burden. It does contribute genuine behavioral context — sessions are scoped to 'this MCP server instance,' so the listing is ephemeral — but it omits safety profile (read-only vs mutating), pagination/limits, and whether sessions are ever pruned or expire.

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 core purpose and the scope qualifier, then the returned fields, then the actionable follow-up. No filler or repetition of structured fields.

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-parameter list tool with no output schema and no annotations, the description covers purpose, output fields, and lifecycle scope adequately. The remaining gap — return volume or ordering — is minor given the low complexity of the 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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter guidance is needed or missing.

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 ('List Cursor agent sessions') and adds scope ('created during this MCP server instance') plus returned fields (session IDs, models, prompts). It is clearly distinguishable from cursor_reply, which it explicitly references, though it does not position itself against cursor_agent, cursor_models, or cursor_health.

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 sentence 'Use session IDs with cursor_reply to continue a conversation' implies the reason to call this tool (to obtain IDs for continuation), but it never states when this tool should be chosen over siblings, nor any condition under which it is unnecessary. Usage is inferable rather than stated.

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