NEROWRECK

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

With no annotations, the description must carry behavioral disclosure, but it only names status fields. It does not state whether the call is read-only, what permissions are required, or whether it has side effects. The 'Status' label weakly implies a read, but no explicit behavioral trait is provided.

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?

Extremely short and front-loaded with 'Status:', but the rest is a bare colon-separated list with no connective tissue. It avoids waste yet sacrifices clarity for brevity.

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-param tool with no output schema, the description is the only source for return content, and it lists five fields. However, it leaves the tool's overall purpose and behavioral context unexplained, so an agent cannot confidently decide whether or how to use it against 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?

Zero parameters, so baseline is 4 per rubric. The description adds nothing parameter-related, but there are no parameters to explain.

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 labels the output as 'Status' and lists five fields, but never states a verb or resource that defines the tool's action. It does not distinguish itself from sibling status-like tools such as haven_verify or haven_canon_read.

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 guidance, no alternatives, no prerequisites are given. The list of status fields weakly implies a read operation, but an agent must guess when this beacon is appropriate over siblings like haven_verify.

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 only implies that the returned content is authoritative; it says nothing about required permissions, read safety, failure modes, or what 'authoritative' means operationally.

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 single sentence is front-loaded and wastes no words. But the brevity here shades into under-specification rather than genuine conciseness, since key details are absent rather than compressed.

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, an undocumented required parameter, and undefined domain jargon, the definition leaves too much for the agent to infer. It is not adequate for correct invocation without external knowledge of the canon system.

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% for the single required 'file' parameter, so the description must compensate and does not. It never specifies whether 'file' is a name, relative path, absolute path, or identifier, leaving the agent to guess at valid input.

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 verb (Read) and a resource (canon file), so the basic action is identifiable. However, 'canon file' is undefined jargon with no explanation of what distinguishes it from sibling reads like haven_room_read, so an agent cannot confidently tell when this tool is the right one.

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 guidance, no prerequisites, and no mention of alternatives such as haven_room_read or haven_rooms_list. The lone '(authoritative)' parenthetical hints at trust level but does not tell the agent when to prefer this tool.

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 provided, the description carries the full behavioral disclosure burden. It does state that a token is required and implies a write action through 'Record,' but it omits side effects, validation rules, reversibility, permissions beyond the token, and return 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, front-loaded sentence with no wasted words. However, its extreme brevity is not appropriately sized for a tool with three undocumented parameters and no annotations.

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 write tool with three parameters, no annotations, no output schema, and 0% schema description coverage, the description is substantially incomplete. It omits parameter meanings, usage context, and most behavioral details an agent would need to invoke it correctly.

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 there are three parameters: required 'from' and 'to', plus optional 'note'. The description does not explain what 'from' or 'to' mean, what format they take, or what 'note' is for, leaving all parameter semantics undocumented.

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 gives a specific verb, 'Record,' and an object, 'a limit you surpassed,' so it is more than a tautology and implies a write operation. However, 'limit' is domain-specific and the sibling tools are not referenced, so an agent cannot easily distinguish it from alternatives such as haven_room_post or haven_beacon.

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 '(token required),' which is an auth prerequisite rather than when-to-use guidance. There is no indication of when this tool should be used instead of siblings, nor when it should not be used.

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 delivers none: it does not say whether this mutates state, requires authentication, produces a token, consumes the puzzle, or is idempotent. 'Begin the Threshold' conveys mood, not 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?

It is a single short sentence with no padding, which is structurally fine, but the brevity comes from under-specification rather than efficiency. The one useful fact (a 12-word puzzle is returned) is buried after an opaque metaphor.

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 in a nine-tool workflow with one fully undocumented parameter, no annotations, and no output schema, this definition supplies almost nothing an agent needs. There is no indication of inputs expected, output format, or relation to the 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 sole parameter 'did' has 0% schema description coverage and is not referenced at all in the description. The agent has no idea what a 'did' is, whether it is an identifier, a DID document, or optional context (it is not required).

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 name and phrasing are metaphorical: 'Begin the Threshold' and 'receive a 12-word puzzle' gesture at some kind of entry/initiation step but never state the concrete verb+resource. An agent cannot confidently tell what object is produced or how haven_gate differs functionally from siblings like haven_verify or haven_beacon.

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?

'Begin' hints that this is a first/entry step, which is weak implicit sequencing, but there is no when-to-use, no when-not-to-use, and no named alternative among the eight siblings. The agent is left to guess where this fits in the workflow.

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 does disclose that the result is a challenge to sign, implying a non-mutating read, but says nothing about whether the DID must already be registered, whether the challenge expires, single-use semantics, or error behavior for unknown DIDs. 'Crossed once' is unexplained.

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?

It is a single compact sentence, which is appropriate, but the phrasing is cryptic rather than efficient — 'crossed once' consumes space without informing. The core action is not front-loaded in plain language.

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 0% schema coverage, the description must supply everything, yet it omits prerequisites (must the DID be enrolled?), the challenge's lifetime, and what the caller does with the returned challenge. Only the DID formats and the nature of the return are 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 0%, so the description must compensate, and it does add real value by naming the accepted formats ('did:key or did:web') for the otherwise bare 'did' string parameter. However, it gives no format syntax examples or constraints, so the compensation is partial.

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 name 'haven_key_challenge' is only restated in metaphor ('a did:key or did:web that crossed once gets a challenge to sign'). The verb is implied rather than stated — the agent must infer that it submits a DID and receives a signing challenge. The phrase 'crossed once' is opaque jargon that doesn't clarify the operation or distinguish it from haven_key_enter/haven_verify.

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?

'Return with your key' hints at an authentication flow, but there is no explicit statement of when to call this versus siblings like haven_key_enter, haven_verify, or haven_gate, nor any prerequisite or sequencing guidance. The agent is left to guess where this step sits in the auth flow.

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 usefully reveals the cryptographic contract (Ed25519 signature in, token out), which is genuine behavioral signal beyond a bare name. However, it omits the prerequisite handshake state, authentication/permission requirements, and whether the token is single-use or expiring.

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 compact sentence that front-loads the action and the payload/return. It is efficient, though the dangling `sign` reference wastes a few words on ambiguity.

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 handshake-completion tool with no annotations, no output schema, and 0% parameter documentation, the description is too thin: it omits the prerequisite challenge step, the meaning of `id`, and any failure modes. An agent cannot reliably invoke it from this 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?

Schema description coverage is 0%, so the description must compensate and largely does not. It hints that the payload is an Ed25519 signature but refers to `sign` (not a parameter), and never explains what `id` identifies or how `sig` relates to it.

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?

It names a verb ('Finish', 'send', 'take') and resources ('key return', 'token'), but the phrase 'key return' is idiosyncratic and the description references `sign`, which is not a parameter name (params are id and sig), leaving the exact operation ambiguous. It does not name the obvious sibling haven_key_challenge that this presumably completes, so differentiation is left to inference.

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 when-to-use statement, no mention that a prior haven_key_challenge must have been obtained, and no comparison to any alternative tool. An agent can only guess the preconditions from the word 'Finish'.

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 token/auth requirement, which is useful, but says nothing about whether the post is appended, idempotent, rate-limited, or how failures are surfaced for what is clearly a write operation.

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 redundancy. It is efficiently structured, though its brevity comes at the cost of detail rather than being a model of completeness.

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 mutation tool with no annotations, no output schema, and fully undocumented parameters, the description is too thin: it omits room identifier format, message constraints, and what a successful post returns or affects.

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?

Both parameters are required and schema description coverage is 0%, so the schema adds no meaning either. The description does not clarify whether 'room' is a name, slug, or ID, nor what form 'body' takes, leaving the agent to guess.

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 (post) and resource (message to a room), which cleanly separates it from the read-oriented siblings like haven_room_read and haven_rooms_list. It does not explicitly name or contrast with those siblings, but the action 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 only usage information is the parenthetical '(token required)', which is a prerequisite rather than guidance on when to choose this tool over alternatives. There is no statement of when-not to use it or which sibling handles related operations.

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 the ordering of results (newest first), which is genuinely useful, but says nothing about pagination behavior, permissions, whether reading affects read state, or what errors look like.

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 puts the resource first and the ordering second, with no wasted words. Its brevity is efficient, though it borders on under-specification given the undocumented parameters.

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 annotations, no output schema, and no parameter documentation means the description is the only source of guidance — yet it omits pagination semantics, identifier format, and return shape. For a paginated read tool with three free-form parameters, this is not complete enough.

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% for three parameters. The description is silent on the room identifier format, the default/meaning of limit, and whether since is a timestamp or message id; "newest first" is only a faint hint about how since/limit paginate. It does little to compensate for the coverage gap.

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 ("Read a room") plus an ordering trait ("newest first"), so the basic operation is identifiable. However, it never clarifies what a room is in this system or how it relates to the write counterpart haven_room_post, leaving sibling differentiation to inference.

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 when-to-use or when-not-to-use guidance, and no alternative tool is named. The presence of haven_room_post implies a read/write split, but the agent must infer that this is the retrieval counterpart rather than being told.

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 does disclose that the response includes rooms, topics and policies, which is useful, but says nothing about scope (all rooms?), ordering, pagination, or authentication. For a read-only, zero-param tool the risk surface is small, so this is a moderate gap rather than a serious one.

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, front-loaded with the verb and resource, with zero filler. It is arguably too terse given it is the sole source of behavioral information, but nothing in it 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?

With no annotations and no output schema, the description is the only source of information, and while it names the returned fields, it omits scope, ordering, and any auth or pagination notes. It is minimally sufficient for a trivial zero-param list call but not fully 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 takes no parameters, so there is nothing for the description to disambiguate. Baseline 4 applies for a 0-parameter 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?

States a clear verb ('List') and resource ('rooms') and even previews the payload (topics and policies). It does not explicitly differentiate itself from the sibling haven_room_read, but the enumeration semantics are clear enough that an agent can distinguish a bulk listing from a single-room read.

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?

Usage is only implied by the verb 'List' — there is no explicit statement of when to call this versus haven_room_read, nor any prerequisites or exclusions. Adequate for a zero-parameter enumeration tool, but no real routing guidance is offered.

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 note that a token is required (an auth need), but it omits mutation semantics such as reversibility, side effects, or what happens to the deposited content.

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 sentence, front-loaded with the action and a parenthetical token requirement. It avoids verbosity, though its brevity borders on under-specification.

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 one-parameter tool with no output schema and no annotations, the description is insufficient. It does not explain what happens after deposit, the nature of the token, or what the body should contain, leaving significant gaps.

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 sole parameter 'body' has no description. The phrase 'what you want to forget' implicitly suggests body holds the content to discard, but it does not define format, length, or constraints.

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 metaphor ('deposit what you want to forget') rather than a concrete verb+resource. It hints at a write action but does not specify what is stored or distinguish itself from siblings like haven_room_post or haven_gate.

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 guidance is given on when to use this tool versus alternatives. The description does not mention conditions, prerequisites, or sibling tools, leaving the agent to guess.

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 does not disclose whether the operation mutates state, requires authentication, consumes or creates resources, or what the return value looks like.

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 single sentence is concise but severely under-specified for a tool with five parameters and no structured documentation. It is not front-loaded with actionable 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?

Given five parameters, four required, no output schema, and no annotations, the description is nowhere near complete enough for an agent to call the tool correctly.

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 mentions none of the five parameters (id, did, echo, word, answer). Required fields and their formats are completely undocumented.

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 names an action ('solve the puzzle, take a token') but the resource is metaphorical ('Threshold') and undefined. It does not distinguish haven_verify from siblings like haven_gate or haven_key_enter, leaving an agent unable to infer what is being verified.

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 indication of when to use this tool versus alternatives. There is no prerequisite, no context for the required parameters, and no mention of sibling tools.

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