Registry Rot Watch

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

No annotations are supplied, so the description carries the full disclosure burden. It reveals the entitlement precondition, which is useful, but says nothing about what the watch actually does (polling cadence, how changes are surfaced, whether it persists, or what it returns).

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; the action and its precondition are stated immediately. It is tight, though the brevity comes partly from under-specification rather than efficient 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?

With no annotations, no output schema, and an empty parameter object, the description is the only information source, and it leaves key questions unanswered: how the endpoint is specified, what happens after the watch is created, and how change notifications are consumed.

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, which normally sets a baseline of 4. However, the description explicitly references 'an endpoint' as the thing being watched, yet the schema exposes no way to identify that endpoint, creating a mismatch an agent must resolve by inference.

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 (watch) and resource (an endpoint) plus the observed target (status/contract changes), so the action is unambiguous. It does not, however, differentiate itself from the sibling list_watches or explain how a watch relates to get_verdict/probe_endpoint.

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 only guidance is the parenthetical prerequisite '(watch entitlement required)', which is a precondition rather than usage guidance. Nothing says when to create a watch versus calling probe_endpoint or get_verdict, and no alternatives are named.

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 disclose genuinely useful traits absent from structured data: per-call cost and a one-free-trial-per-operator limit. However, it says nothing about authentication, freshness/latency of the 'latest' verdict, or error 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?

A single short sentence with the resource first and the cost caveat parenthetically attached; nothing is padded or redundant.

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 tool with no output schema the description is nearly sufficient, but it never explains what a 'verdict' payload contains or how the endpoint is scoped, and it offers no routing relative to the four sibling tools.

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 declares zero parameters (baseline 4), but the description refers to 'an endpoint' as if it were an input, implying a selector that the schema does not expose. This mismatch leaves the agent unsure how the target endpoint is identified, so the description adds ambiguity rather than meaning.

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 ('latest vault verdict for an endpoint'), which is more than a tautology, but 'verdict' and 'vault' are undefined jargon and the sibling relationship to probe_endpoint or successor_check is never clarified. An agent cannot confidently tell what a verdict is or how this differs from the other lookup tools.

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 only contextual information is pricing ('$0.01/call; one free trial query per operator'), which hints at cost sensitivity but gives no when-to-use or when-not-to-use guidance. Nothing says when to call get_verdict versus probe_endpoint or successor_check.

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 burden and does disclose meaningful behavior: the probe is 'live' (not cached), 'anonymous' (no auth), has a side effect ('stored to the vault'), and costs $0.01/call. Missing are rate limits and what happens on failure, but this is above average disclosure for an unannotated 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?

A single front-loaded sentence with no waste; cost, liveness, and anonymity are packed in efficiently. 'Stored to the vault' is slightly cryptic, costing a perfect score.

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 an empty-schema, no-output-schema, no-annotation tool, the description should at least clarify how the endpoint is selected and what a probe returns. It conveys cost, anonymity, and the vault side effect but leaves the target-selection and result-shape questions unanswered.

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?

Zero parameters, so baseline is 4 per the rubric. The description adds no parameter semantics, which is expected here, though it also never explains how the target endpoint is supplied without any input field.

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 ('probe an endpoint') and is clearly distinct from siblings like add_watch, get_verdict, and list_watches. The added qualifiers 'live' and 'anonymous' sharpen the intent. It falls short of 5 because the mechanism for identifying which endpoint is never clarified, given the empty 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?

No when-to-use or when-not-to-use guidance, and no mention of alternatives despite four sibling tools. The only usage-relevant detail is the '$0.01/call' cost, which is a reason to prefer caching but is not framed as such.

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 usefully discloses a cost trait ('$0.01/call'), which is real context beyond structured fields, but says nothing about whether the call mutates state, what it returns, or its auth/rate-limit profile.

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 tight sentence with no filler, and the core resource is front-loaded before the cost note. It is arguably too terse for a tool whose return value is undefined, but nothing is wasted.

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 tool with no output schema, the description need not enumerate return fields, but 'verdict' is left entirely undefined and the relationship to the get_verdict sibling is unexplained, leaving a real gap in how an agent would 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 takes zero parameters, so there are no parameter semantics to document; the baseline of 4 applies. The description's only 'input' concept (the stored snapshot) is contextual rather than a parameter.

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 phrase 'successor-contract verdict' names a resource and the 'stored pre-move snapshot' names its source, but there is no clear verb and the jargon is unexplained. Critically, a sibling named get_verdict exists and the description does nothing to distinguish this tool from it, leaving an agent unsure which verdict tool to pick.

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 gives no when-to-use, when-not-to-use, or alternative guidance. 'Stored pre-move snapshot' hints at a precondition but never states it as a trigger condition, and nothing routes the agent between this and get_verdict.

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