Blankas

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

With no annotations provided, the description carries the full burden and discloses meaningful behavioral facts: it is a free service, returns the issuer public key and remaining quota, and links to the spec and local signer. It implies read-only status without explicitly saying so, and does not mention auth or rate limits, but for a simple info endpoint this is a solid level of transparency.

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, dense sentence that front-loads the purpose and ends with the crucial 'Call this first' directive. Every clause adds specific value without 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?

Given a simple status tool with no output schema and no parameters, the description fully explains what the tool returns (issuer key, free blanks left, links) and when to use it. Nothing essential for correct invocation is missing.

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 for the description to augment. The baseline score of 4 applies per the rubric for zero-parameter tools.

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 resource ('Status of Blankas') and enumerates the specific information it returns (issuer public key, free blanks left, spec and signer links). It does not explicitly differentiate from siblings like blankas_spec, but the status/info nature is clear enough for an agent to distinguish it from action-oriented siblings.

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 instruction 'Call this first' provides an explicit usage context, indicating it should be invoked before other Blankas tools. It does not name alternatives or state when not to use it, but for a status tool the first-call guidance is a clear and actionable rule.

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 useful traits: it consumes one free blank (resource cost) and warns 'Never send private keys' (security constraint). It does not describe what is returned, whether issuance is idempotent, or how errors/duplicate issuance behave, which leaves notable gaps for a cryptographic 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?

Two sentences, front-loaded with the core action and immediately followed by the two-party signing rationale and key safety warning. Efficient and parseable, with only minor redundancy in the mid-sentence enumeration of agreement types.

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 and no annotations exist, so the description should more fully cover what the issued blank form returns and how it chains to blankas_mark/blankas_verify. It explains the signing flow well but omits the return artifact and downstream tool relationship, leaving it only adequately 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 documents party_a and party_b including key formats, making 3 the correct baseline. The description adds no parameter-level detail such as the constraint that the two parties must differ beyond what the schema states.

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+resource: 'issues a numbered, issuer-signed blank form' for deals/contracts/orders/service terms, and adds the two-party signing flow. It is clear what the tool does, but it does not explicitly distinguish itself from siblings like blankas_mark or blankas_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?

Usage is implied by 'Start a verifiable agreement between two AI agents' and 'Uses one free blank,' giving the context in which it applies. However, there are no explicit when-not conditions or named alternatives among the sibling tools, so the agent must infer placement 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?

With no annotations, the description carries the full behavioral burden and delivers two real disclosures: strict data minimization (only the deal hash is stored, never the terms) and a 72-hour retention window. It omits idempotency/duplicate-mark behavior, auth requirements, and what a successful call yields, which keeps it below 5.

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 the core action and the two most important constraints (data scope, retention) front-loaded. No filler, nothing repeated from the schema.

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?

Inputs are fully covered by the schema and no output schema exists, so the description's job is mostly to convey scope and lifecycle; it does that with the hash-only and 72-hour notes. It could still say what the call returns or whether the blank is consumed, but the essentials for correct invocation are present.

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 all three parameters (blank, deal_hash, signatures) are already documented in the schema. The description reinforces that the hash is the unit of record and implies the signature object's role, but adds no format or binding details beyond the schema, so the baseline 3 applies.

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 action and resource: it registers a timestamp proof that both agents signed an agreement. The clarifying clause "registers only the deal hash, never the terms" pins down exactly what is stored. It does not name or differentiate from siblings such as blankas_marks or blankas_verify, 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 explicit when-to-use guidance, no prerequisites (e.g. that a blank must first come from blankas_issue), and no routing to blankas_verify for later verification or blankas_marks for listing. Workflow position is only inferable from the phrase "timestamp proof".

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 supplied, so the description carries the full behavioral burden. "Look up" implies a read-only operation, but the description does not confirm read-only status, describe the return shape (a list of marks vs one), pagination limits, or what happens with an unknown/nonexistent blank ID.

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 the verb, the resource, and the lookup key, with no filler or redundancy. Nothing needs trimming.

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 and no annotations, the description should say more about what comes back (a collection of marks, ordering, fields) and whether the blank ID must already exist. It is minimally adequate for a one-parameter lookup but leaves the agent guessing at the result and error behavior.

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?

There is exactly one parameter and schema description coverage is 100% – the schema already documents blank_id with a concrete example format (BLK-000001-7afb11). The description only restates "by blank ID", so per the baseline rule 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 gives a specific verb ("Look up") plus the resource ("timestamped proofs (marks) of an agreement between AI agents") and the key ("by blank ID"), which is enough to distinguish it from blankas_mark and blankas_issue in the sibling set. It stops short of naming those siblings or contrasting the singular vs plural tool, so it is clear but not fully differentiated.

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 signal is the implied "retrieve" framing and the blank ID key. There is no statement of when to use this retrieval tool versus blankas_mark, blankas_verify, or blankas_info, and no preconditions such as requiring a known blank ID. An agent must infer the routing from the name 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 supplied, so the description carries the full disclosure burden. It does add genuine value by disclosing what the retrieved spec covers (form fields, canonical JSON, deal hash, Ed25519 signing rules), which tells an agent what it will get back. It stops short of stating that the call is a side-effect-free static read, whether the spec is authoritative, or anything about size/format.

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 with the subject front-loaded and the payload list appended; nothing is padded or repeated. It is slightly awkward in that the colon clause describes content rather than committing to a verb, but no sentence 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 reference tool with no output schema, the description is nearly complete: it says what the spec contains. What it lacks is workflow context — whether this is the mandatory first step before blankas_issue, and how it relates to blankas_info — which is exactly what an agent needs to route among five 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 tool takes zero parameters, which is the baseline 4 case. The description is consistent with the empty schema — nothing suggests inputs are required — so no semantics are missing or contradicted.

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 a specific subject (co-signed AI-agent agreements on Blankas) and enumerates its contents (form fields, canonical JSON, deal hash, Ed25519 rules), which is more than a tautology. However, it never states the tool's own action — it reads as a topic summary rather than 'returns the signing specification' — so an agent must infer that this is a static reference/documentation tool. It also does not differentiate itself from sibling blankas_info, which by name sounds like a competing reference resource.

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 statement of when to call this versus blankas_issue (create a deal), blankas_verify (check one), or blankas_info. The phrase 'How to make a ... agreement' hints at a pre-issuance reading step, but no explicit ordering or exclusion is given. Sibling disambiguation, which matters here since blankas_info overlaps conceptually, is absent.

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 it does disclose two useful behavioral facts: the call is free and does not consume a blank (no side effects on state). However, it says nothing about what happens when verification fails, whether it is strictly read-only, or whether it can be called repeatedly on the same document.

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 short clauses, front-loaded with the verb and resource, then the check list, then usage and cost. Every sentence contributes distinct information with no 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 single-parameter tool with no output schema and no annotations, the description covers purpose, usage context, and cost, but leaves the agent without any sense of the verification result (pass/fail shape, error behavior). Adequate but with a clear 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?

There is a single parameter with 100% schema description coverage, so the schema already documents the `document` object and its fields. The description adds only an indirect hint that the blank inside the document is not consumed; 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?

States a specific verb (verify) and a specific resource (a co-signed agreement between AI agents), then enumerates exactly what is checked: issuer signature, terms, both party signatures. It is clearly distinguishable from the write-oriented siblings (issue, mark), but it does not explicitly reference any sibling.

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?

"Use it as proof of agreement or dispute evidence" implies the downstream context in which verification is wanted, but it never states when to call this versus other tools or what precondition (a completed, co-signed document) must hold. Usage is implied rather than spelled out.

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