Combined Server-Surface Census

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

No annotations exist, so the description carries the full burden. It usefully discloses the 'watch entitlement required' prerequisite, but says nothing about whether watchers are persistent, idempotent, or what side effects/notifications a watch produces.

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 short sentence that is front-loaded with the action and scope. It is appropriately terse, though its terseness contributes to the missing mechanics noted elsewhere.

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 annotations, no output schema, and no parameters, the description is too thin: it does not explain how the endpoint is selected, what a watch object contains, or how it relates to the sibling snapshot and verdict tools. The entitlement note is helpful but insufficient.

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, which is the baseline-4 case under the scoring rules. There is no parameter schema to elaborate on, and the description correctly does not invent parameters.

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 provides a specific verb ('Watch') and resource ('an endpoint') plus the purpose ('status/surface changes'), which differentiates it somewhat from the sibling list_watches (list vs add). However, it leaves the core mechanics vague: with zero parameters, it never explains which endpoint is watched or how it is identified, so the agent cannot fully tell what the tool operates on.

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 when-to-use or when-not-to-use guidance is given, and no alternatives are named. It doesn't explain how this relates to list_watches, take_snapshot, or combined_verdict, leaving the agent to infer that this is the setup step.

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 behavioral burden. It does add genuinely useful cost and quota context ($0.01/call, one free trial per operator), but omits whether the operation is read-only, what a 'verdict' contains, what 'signed' implies about authorization, and how two snapshots are identified when the tool takes no parameters.

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 with no padding; the parenthetical cost/trial note is compact and carries real operational value. Slight cost in that the pricing aside occupies space that could have gone to the actual diff semantics.

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?

No output schema exists, so the description must explain what a verdict looks like and how snapshots are selected, and it does neither. Combined with no annotations and no parameters, an agent cannot reliably invoke this tool from the definition alone.

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 rule for zero-parameter tools is a baseline of 4, but here the description actively implies inputs ('diffing two signed snapshots') that the empty schema does not expose, leaving the agent unable to tell how the snapshots are supplied. That mismatch justifies a deduction from the baseline.

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 core action — diffing two signed snapshots to produce a verdict — is identifiable, but 'composed verdict' is undefined jargon and it is never said which two snapshots or where they come from. A reader can tell it relates to the snapshot family (take_snapshot, list_snapshots) but not precisely what output it yields.

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 statement of when this should be used instead of list_snapshots or take_snapshot, and no prerequisites for the 'signed snapshots' precondition. The only usage-adjacent content is a trial/pricing note, which is not selection 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?

No annotations are provided, so the description carries the full behavioral burden, yet it says nothing about ordering, scope (all snapshots vs. a workspace/user), pagination, or permissions. Only the read-only nature is implied by the verb "List".

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 with no filler or repetition. It is efficient, though its brevity contributes to the gaps flagged elsewhere.

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 is the only source of information about what a "stored snapshot" is and what the list returns (count, ordering, identifiers). It supplies none of that, leaving the agent to call blind.

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 is an empty object, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly avoids inventing parameter behavior.

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-resource pair ("List ... snapshots"), so an agent knows this is a read operation over stored snapshots. It does not explicitly distinguish itself from the closest sibling take_snapshot (which creates one) or explain how snapshots relate to watches, so it stops short of a 5.

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?

There is no guidance on when to call this versus take_snapshot for creating a snapshot or list_watches for the watch list. The agent must infer the read-vs-write split from the names alone.

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, and it discloses almost nothing. It implies a read of the caller's own watches, but says nothing about return shape, pagination, ordering, filtering, or permissions.

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 short sentence with no filler, and the verb/resource is front-loaded. It is efficient, though arguably under-specified rather than optimally concise.

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 output schema, no annotations, and no parameters, the description is the only source of information, and it omits what a 'watch' or 'alert' is and what the listing returns. For a list tool with an empty schema, the agent is left guessing at the response shape.

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 clarify beyond the schema. Baseline 4 applies for a parameterless tool.

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 ('List') and resource ('watches and alerts'), which an agent can distinguish from the sibling add_watch. However, it never explicitly contrasts itself with the other siblings (get_verdict, probe_endpoint, successor_check), so sibling differentiation is left implicit.

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?

There is no guidance on when to use this versus add_watch or the other siblings, and no stated conditions or prerequisites. The agent must infer that this is the read counterpart to add_watch purely from the name.

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 behavioral burden and does disclose that this is a one-time operation costing $1.99, which is useful context. However, it does not state whether invoking immediately charges the user, what side effects occur, how 'pin or verify depth' behaves, or whether the action is reversible.

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 short, front-loaded fragment with no wasted sentences. Its brevity is appropriate, though the phrasing is cryptic rather than perfectly 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 paid action tool with no annotations, no output schema, and no parameters, the description is too thin. It does not explain what a 'combined snapshot' returns, what 'pin or verify depth' means, or when the tool should be used instead of its siblings.

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, so there is no parameter semantics to explain beyond the schema's empty object. Baseline 4 applies because the schema is complete for a no-arg tool.

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 identifies a one-time combined snapshot and mentions pin/verify depth plus a $1.99 price, but 'combined' and 'pin or verify depth' are unexplained jargon. It does not clearly distinguish this action from sibling tools such as list_snapshots or combined_verdict.

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?

There is no explicit guidance on when to choose this tool over alternatives like list_snapshots, add_watch, or combined_verdict. The agent is left to infer usage from the phrase 'one-time combined snapshot' and the price.

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