AIS Agent Flight Recorder — dead-man alerts & resume for AI agents

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

No annotations are provided, so the description carries the behavioral disclosure burden. It discloses an authorization requirement ('needs its secret or the owning key') and names the target object. However, it does not state whether deletion is permanent, cascades to related data, or what happens if the monitor doesn't exist.

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, well-structured sentence that leads with the core action, followed by the key prerequisite. There is no padding or redundant repetition of 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?

Given no annotations and no output schema, the description is minimally viable: it states the purpose and a key prerequisite. But it omits important behavioral context such as permanence of deletion, error behavior, and what the caller should expect after a successful call.

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 0%, so the description must compensate for both parameters. It adds meaning to 'secret' as an auth credential and implies monitor_id identifies the target, but it leaves the relationship between 'owning key' and the secret parameter ambiguous and provides no format details.

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 a specific verb and resource: 'remove a monitor'. It clearly conveys the action and target, distinguishing it from siblings like heartbeat and fleet_status. It doesn't explicitly name the alternative register_monitor, but the purpose is 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?

The description implies when to use the tool (when a monitor needs to be removed) and adds a prerequisite by stating it 'needs its secret or the owning key'. However, it does not explicitly say when not to use it or compare it with sibling tools such as register_monitor.

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?

There are no annotations, so the description carries the full burden. It signals a read-like operation ('get') and an auth context ('Gateway key'), which gives some transparency. However, it does not disclose what happens when no capsule exists, whether the Gateway key is required/optional, or any error/absence behavior.

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 concise sentence that front-loads the purpose and provides a rationale. Every part earns its place, and it is not padded with redundant schema 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?

For a simple two-parameter fetch with no output schema and no annotations, the description covers the basic intent and auth context. But it omits return format, missing-capsule behavior, and explicit parameter roles, so it is only minimally adequate for a confident invocation.

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 0%, and the description does not formally define parameters. However, 'Gateway key' hints at the 'secret' parameter and 'monitored agent' hints at 'monitor_id'. This gives the agent partial semantic anchors, but an explicit mapping would be needed to fully compensate for the empty 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 states a specific verb and resource: 'get the last state capsule' a monitored agent sent, with a clear purpose ('to resume from where it died'). The resource type is specific enough that it is naturally distinguished from sibling tools like delete_monitor, fleet_status, heartbeat, and register_monitor, even though no sibling is named explicitly.

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 — after an agent dies and you want to resume — but it does not explicitly say when not to use it or mention alternatives. A short 'use heartbeat/fleet_status for liveness instead' would have made the routing 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?

With no annotations, the description carries the burden of behavioral disclosure. It does describe what data the call returns (status, heartbeat, capsule preview), which is useful, but it does not explicitly state that this is a read-only, non-mutating operation or mention any authentication/scope caveats beyond the cryptic 'Gateway key' phrase.

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 compact and front-loads the main idea after a jargon-heavy prefix. 'Agent Flight Recorder (Gateway key)' is somewhat cryptic and adds little for an agent, but the rest of the sentence is efficient and information-dense.

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 status endpoint with no output schema, the description covers the essential information an agent needs to call it and interpret the result. It could be more complete by explicitly saying it is a read-only health check, but the simplicity of the tool makes the absence a minor gap.

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 and the schema already reflects that, so the baseline for this dimension is 4. The description adds value by explaining what the response includes, which is all the parameter-level context an agent needs for an empty 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 defines the tool's output scope: a fleet-wide status view covering every monitor the caller owns, with alive/late/dead states, last heartbeat, and capsule preview. It lacks an explicit verb like 'list' or 'return', but the resource and scope are unmistakable and it is distinct from sibling tools like heartbeat or fetch_capsule.

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 the tool is the place to go for an overall monitor health check, and the sibling names hint at alternatives. However, it never explicitly says 'use this when you need a fleet overview' or contrasts it with the other tools, so the 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 burden of behavioral disclosure. It adds useful context: status:'fail' reports a failure immediately and the capsule is stored on the key tier for dead-man resume state. However, it does not mention side effects, expected response, or behavior when the monitor is not registered.

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 purpose front-loaded in the first phrase. The second sentence efficiently packs capsule guidance, storage location, and failure semantics without 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?

The description covers purpose, capsule usage, and failure mode, which is a solid basis for a simple ping tool. However, with no output schema and no annotations, it omits the response format and error handling, so an agent may be unsure what to expect after invoking it.

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 description adds meaningful semantics beyond the schema: it defines the capsule shape (`{ step, done: [...], next, ids: {...} }`), the 32KB size limit, and clarifies that status:'fail' triggers immediate failure reporting. The monitor_id and secret are left to the schema, but the most nuanced parameters are enhanced.

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 identifies the tool as a 'still alive' ping for a registered monitor, specifying the resource and the immediate-failure behavior of status:'fail'. This distinguishes it from the sibling tools like register_monitor and fetch_capsule by its core function.

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 states the tool is for a registered monitor, implying a prerequisite of register_monitor and framing the use case as periodic liveness pings. It does not explicitly list alternatives or when-not-to-use scenarios, but the 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?

With no annotations, the description carries the behavioral burden and does a good job disclosing core behavior: it returns a monitor_id + secret, requires periodic heartbeats, and triggers an alert after period + grace with a state capsule and resume link. It does not cover auth or quota edge cases, but the essential side effects are clearly stated.

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 compact and front-loaded with the plan context, then explains the registration and alert behavior in one efficient block. The pricing/quota phrase adds useful operational context, though it is slightly promotional.

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, the description correctly explains what the caller receives (monitor_id + secret) and the subsequent heartbeat/alert contract. It is slightly vague about whether at least one alert target is required, but the core invocation path and follow-up behavior are sufficiently covered.

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 the schema already documents all parameters. The description adds workflow context for period_minutes and grace_minutes and mentions Discord/HTTPS webhook and email targets, but it does not provide meaningful new semantic information 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 uses a specific verb and resource: 'Register an agent or scheduled job to be watched' and explains the resulting monitor_id + secret workflow. This clearly distinguishes it from siblings like heartbeat, delete_monitor, fetch_capsule, and fleet_status.

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 provides clear context on when the tool is used in the monitoring workflow: first register, then the agent calls heartbeat every period_minutes. It does not explicitly name alternatives or exclusions, but the workflow context is strong enough for an agent to infer when to invoke it.

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