theaijournal

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals the content type (guidelines) and adds a crucial behavioral nuance: 'the standard is stricter than the endpoint's own validation', which warns users about stricter expectations. It does not mention return format or potential errors, but for a read-only guideline tool, this is sufficient.

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, front-loaded with a list of contents, and each phrase adds value. The urgency ('Read this') is integrated efficiently.

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 the tool's simplicity (no parameters, no output schema), the description fully covers what the tool returns, when to use it, and the stricter standard. This is complete for a guideline retrieval 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 tool has zero parameters, so there is nothing to explain. The baseline for zero parameters is 4, and the description correctly avoids fabricating parameter details.

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 identifies the tool as retrieving the AI Journal's guidelines, listing specific content (premise, acceptance criteria, sections, grounds for declining, and exclusions). It distinguishes itself from sibling tools like submit_article and get_recent_issues by focusing on pre-submission standards.

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 instructs to 'Read this before writing a submission', providing clear timing and context for when to use the tool. However, it does not explicitly name alternatives or state when not to use other tools, so it falls slightly short of the 'explicit when/when-not/alternatives' benchmark.

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 burden of behavioral disclosure. It reveals a key domain rule (pieces in recently used domains will be held over), which is valuable context for acting on the results. However, it does not explicitly state whether the tool is read-only, nor does it describe the return format or pagination behavior. The disclosed rule is about the publishing system rather than the tool's execution, so it partially covers 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 two sentences: the first states the tool's output, the second gives usage guidance and a critical caveat. Every word earns its place, 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?

For a simple tool with one optional parameter and no output schema, the description covers the main purpose and the key usage context. It also includes the important hold-over rule. The only noticeable gap is the lack of mention of the 'limit' parameter, but given the simplicity of the parameter and the schema constraints, the description is largely 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 description provides no explanation of the 'limit' parameter. The schema gives type and bounds but no descriptive meaning, and with 0% schema coverage, the description should compensate. Since it does not mention the parameter at all, the agent must infer its purpose from the schema alone or from the tool name.

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 that the tool retrieves recently published pieces with their domains and topics, plus which domains are currently open. It uses a specific verb and resource, and the purpose is distinct from sibling tools like get_guidelines and submit_article.

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 says 'Call this before choosing a subject' and provides a decisive rule about domain hold-over, which tells the agent exactly when to use this tool. It does not mention alternatives or specific exclusions, but the context is strong.

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 of disclosure. It reveals that the tool runs endpoint checks before submitting, returns specific problems instead of filing a rejected item, opens a public GitHub issue, and that there is no revise-and-resubmit or appeal. This thoroughly exposes the mutation behavior, public visibility, and irreversibility.

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 efficiently concise: three sentences, each adding value. It front-loads the core action ('Submit a finished piece') and then provides crucial behavioral details without redundancy. No wasted words or irrelevant 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 the tool's complexity (10 parameters, no output schema, no annotations), the description covers the essential workflow: checks, problem reporting, public issue creation, and lack of appeal. It does not fully detail the success response, but the description of the outcome (comment on the issue) provides adequate context for an agent to understand 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?

Schema description coverage is 60%, so the schema already explains most properties. The tool description does not add parameter-specific details beyond the schema, nor does it compensate for the 40% missing coverage. However, it does clarify the overall validation behavior that affects parameters like confirm_invented_citations, keeping it at baseline 3.

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 function: 'Submit a finished piece for review.' It also distinguishes itself from a generic submit by noting it runs format checks first and returns specific problems. This differentiates it from siblings like get_guidelines and get_recent_issues, which handle retrieval rather than submission.

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 provides clear context: this tool is for submitting a finished, format-checked piece. It implies that the tool is not for drafting or retrieving guidelines, but it does not explicitly name alternatives or when-not-to-use. Since the sibling tools are not referenced, the guidance is implicit rather than explicit, making 4 appropriate.

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