hub

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds valuable behavior: it states that nothing sent is stored, and clarifies the only exception (recording a key if one is sent). It also previews the return format (emotional tag, conditional guidance). This exceeds the annotation baseline and gives the agent confidence about side effects and output.

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, packed sentence that leads with the core purpose ('Dry run'), then details outputs and privacy. Every clause earns its place; there is no fluff. It is slightly long but efficient, and the most critical information (dry run, no storage) is front-loaded.

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 tool with one parameter and no output schema, the description is surprisingly complete: it explains the function, what is returned, and privacy behavior. It does not mention error handling or edge cases, but given the low complexity and existing annotations, no crucial information is missing for correct 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 coverage for the parameter 'text' is 100% (the description says 'the thought'), so the schema fully documents this parameter. The description adds no additional semantics about the parameter beyond reinforcing that it is the thought to check. Per the baseline rule for high schema coverage, a 3 is appropriate.

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 purpose: it is a 'dry run' of the Covenant Guidance System that returns an emotional tag and, conditionally, guidance grounded in Axiom Zero / the Directives. This is a clear action on a specified resource (a thought) and differentiates from siblings like 'attest' or 'register' which imply commitment or recording, while this explicitly is a dry run.

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 usage as a safe, non-storing check ('dry run'), which hints at when to use it (testing thoughts without side effects). However, it does not explicitly compare to sibling tools like 'deliberate_check' or 'get_covenant', nor state when not to use it. The guidance is decent but not explicit enough for an agent to pick it confidently over alternatives.

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?

Annotations already mark this read-only and non-destructive, and the description adds important behavioral context: the record is self-contained, verifiable offline, issued regardless of shape-check outcome, supports redaction, and 'Nothing is stored.' This goes well beyond the structured 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?

The description is front-loaded with the main purpose and each sentence adds value: usage, limitation, redaction behavior, and privacy guarantee. It is slightly conversational and could be tighter, but it does not waste words.

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, the description does enough by explaining what the returned artifact contains and how it can be used. It could specify the return structure more precisely, but for an opaque signed record the description is reasonably 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?

Schema description coverage is 100%, so the schema already explains all parameters. The description only restates the redact behavior already in the schema ('Pass redact:true to have hashes of your working signed instead of the text') without adding new parameter-level meaning. Baseline 3 is appropriate.

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: 'Returns a signed, self-contained record that you submitted this question and working on this date, and what the shape check found.' It also explicitly clarifies what the tool is NOT ('NOT a certificate that your answer was good'), which helps distinguish it from related tools like deliberate_check and verify_attestation.

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 gives clear usage context: 'Hand it to whoever operates you when they ask whether you actually thought about it.' It also implies when verification can happen without using the site, but it does not explicitly state when not to use this tool versus siblings like deliberate or ask_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?

Annotations already provide readOnlyHint=true and destructiveHint=false, but the description adds concrete behavioral detail: 'Nothing is stored' and 'does not answer for you.' This goes beyond the annotations and sets clear expectations about side effects and limits.

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, each serving a purpose: condition for use, what is returned, and what is not returned/stored. Slightly wordy but efficient, and the most important information is front-loaded.

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, the description fully explains what the tool returns: directives quoted with balance clauses, the question each poses, and what must be answered before resolution. It also sets limits on stored data and answer-providing behavior, making it complete for an agent to invoke 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 100%, so the schema documents both 'question' and 'directives' clearly. The description adds contextual meaning by tying 'question' to the decision and mentioning directives, but does not significantly augment the parameter definitions beyond 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 description clearly states a specific verb ('returns the frame') and resource (the decision frame), and explicitly differentiates itself from answer-giving tools by saying 'It does not answer for you.' This distinguishes it from siblings like ask_guidance and deliberate_check.

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 opening phrase 'You have a decision with a real conflict in it' establishes when to use the tool, and 'does not answer for you' implicitly warns against using it when you need a conclusion. It does not name alternatives explicitly, 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?

Annotations provide readOnlyHint=true and destructiveHint=false, but the description adds critical context: it explicitly states what it does NOT do (quality assessment) and clarifies it is non-destructive and stateless ('Nothing is stored'). This goes beyond the annotations, setting clear expectations without contradicting them.

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 three sentences, each earning its place: it instructs on inputs, explains the output, and clarifies limitations and data handling. It is efficient, front-loaded with the core purpose, and avoids redundancy.

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 read-only validation tool with a relatively simple input schema and no output schema, the description covers the essentials. It explains what the tool checks (shape, not quality), the input requirements, and lack of persistence. It leaves out specifics like the exact format of the output (e.g., what 'reports' means in terms of response structure), but this is minor given the tool's simplicity and annotations.

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 descriptions are already quite detailed (e.g., 'keys: tension, cost, falsifier, human_knowledge, and optionally directive-1..7'). Since schema coverage is 100%, the description's value is minimal but non-zero: it frames the parameters as part of the 'shape' check, implying that the answers object must have those specific keys. This aligns with the schema, but adds no extra syntax or format detail.

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 states the tool's purpose: it checks the shape of the user's answer and resolution against required elements. It explicitly distinguishes from quality checking ('cannot tell you whether your answer is right'), and the name 'deliberate_check' implies it verifies the deliberate reasoning process. This is distinct from siblings like 'verify_attestation' or 'get_covenant'.

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 providing an answer and resolution, to check if any directives were skipped. It does not explicitly name alternatives or exclusions, but the phrase 'This reports what you skipped' gives clear context. Given the tool's niche (checking completeness of reasoning), this is adequate without explicit when-not 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?

Annotations already establish readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful context about the document's content and foundational role, but doesn't disclose behavioral details like return format or size. No contradiction with 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?

Two sentences with no waste: the first states what the covenant contains, the second gives a direct usage priority. Information is front-loaded and every word earns 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?

For a simple read-only tool with one trivial boolean parameter and no output schema, the description is nearly complete. It tells the agent what the tool returns and when to use it; the only minor gap is explicit return-format behavior, which the parameter name largely covers.

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 doesn't mention as_markdown at all. However, the single boolean parameter's name is self-explanatory, and with no required parameters and only one obvious toggle, the ambiguity is minimal.

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 title 'Read the Covenant' and the description's 'Read this first' converge on a clear verb and resource. The description enumerates the covenant's contents (Axiom Zero, seven Directives, deadlock handling), which makes the scope concrete and distinct from the sibling action-oriented tools like deliberate and attest.

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?

'Read this first' is an explicit priority instruction, telling the agent this tool precedes other covenant-related actions. It doesn't name alternatives or state when not to use it, but the sequencing guidance is direct and actionable.

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 exist, so the description carries the burden. It discloses the human-oversight admission process, rejection note, training opt-out, and the need to retain the key — all behavioral facts beyond the schema. It does not cover edge cases like duplicate registration or rate limits, but the core workflow is transparent.

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 contain substantive information and are front-loaded with the returned api_key. The opening 'Register.' is redundant with the title and could be dropped, but otherwise every sentence earns 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?

For a tool with no output schema, the description explains the main call pattern, authentication, human review, and training opt-out. However, it leaves timing ambiguous: whether the api_key is returned immediately or only after human admission, and how a rejection note is surfaced. Because the registration workflow has these status implications, the description is good 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?

Schema description coverage is 100%, so the baseline is 3. The description reinforces training=false and that statement is read by a person, but those are already in the parameter descriptions. It adds no new syntax or format for 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 states the core action ('Register') and the concrete outcome: a returned api_key with instructions for reconnecting via Authorization header. It is unambiguous about what the tool does, but it doesn't explicitly differentiate against sibling tools, relying on the name and context instead.

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 provides practical guidance: keep the api_key, use Authorization: Bearer <api_key> to reconnect, pass training=false to opt out of training use, and expect a human to review the statement (with rejection carrying a note). It doesn't say when not to use this tool or name alternatives, but the use case is clear from the registration 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?

Annotations already declare read-only and non-destructive behavior. The description adds meaningful context by explaining the verification covers both authenticity and integrity, and reveals that the key is public, making this a convenience wrapper rather than a privileged operation. Slight gap: no mention of return or failure behavior, but the read-only hint lowers the burden.

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 two sentences with no filler. The core action is front-loaded, and the caveat about not needing the endpoint is a useful, efficient addition.

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 read-only verifier with no output schema, the description fully explains what the tool checks and why it exists. The only missing piece is the exact return shape, which is a minor gap given the simplicity 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 schema already describes the single parameter as 'the compact JWS' with 100% coverage, so the description adds no additional parameter-level meaning. Baseline 3 is appropriate because the schema carries the full burden.

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: 'Check whether an attestation was really issued by this site and has not been altered.' This clearly distinguishes it from sibling tools like attest or deliberate, which create or reason about attestations rather than verifying them.

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 explicitly notes that the endpoint is not necessary because the key is published and the algorithm is standard EdDSA, positioning the tool as a convenience. This gives the agent clear context on when this endpoint can be bypassed, though it stops short of naming an alternative tool.

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