AgentLedger

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

There are no annotations describing side effects, read-only nature, or potential destructive actions. The description does not explicitly state that this operation is non-mutating, and the noun-phrase format leaves doubt about whether it only reads alerts or performs some action.

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 extremely short and relies on a noun phrase. While it avoids fluff, it is too sparse to be considered appropriately concise—it omits essential action and usage information, making it more under-specified than tightly worded.

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 or return behavior is described. The description does not indicate what the tool returns (e.g., a list of alert objects, a count, or a status), leaving a critical part of the tool's contract 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 only parameter, agent_id, is not explained. The description does not clarify what an agent is, how the ID is used, or whether it filters alerts by agent. Without this, an agent cannot confidently construct a correct invocation.

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 is a noun phrase ('Alerts for an agent') rather than a clear verb phrase. It indicates the subject (alerts) and the context (agent, budget warnings, spending spikes) but does not state whether it retrieves, lists, or generates alerts, leaving the tool's action ambiguous.

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 provided about when to use this tool versus sibling tools like ledger_report or ledger_track. It does not mention scenarios where alert retrieval is preferred or how it differs from other tools.

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 bears full responsibility for conveying behavior. It only says 'List all agents,' which implies a read-only operation but does not explicitly state that it has no side effects, does not modify state, or that it returns a list of agent records. Minimal 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, concise sentence with no unnecessary words. It is highly efficient and front-loaded with the key 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?

The description is very thin, providing no information about what is returned (even though an output schema exists), the meaning of 'agents,' or any limitations. Given the sibling tools, more context could be helpful to clarify the exact purpose and expected results.

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 are no parameters, so the description adds no parameter-specific meaning, but the baseline for 0 parameters is 4. The lack of parameters is clear from the schema, and the description does not need to elaborate on them.

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 'List all agents' clearly states the action (list) and resource (agents), and it distinguishes from sibling tools by implying a full listing, which is different from alerts, report, set budget, or track. However, it lacks any scope or context that might clarify what 'agents' refers to, leaving slight ambiguity.

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 provided on when to use this tool versus the sibling tools (e.g., ledger_alerts, ledger_report). There is no mention of use cases, prerequisites, or situations where listing all agents would be preferable to other 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?

No annotations are present, and the description does not disclose whether the tool is read-only or has side effects. While 'report' implies no modifications, that is not explicitly stated.

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 extremely concise and immediately communicates the tool's purpose and output contents in a single sentence. No wasted 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?

The presence of an output schema (per context) means return values do not need explanation. The input schema is fully covered, and the description provides a useful summary of the report's contents, making the tool 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?

The schema fully describes both parameters ('agent_id' and 'days') with clear descriptions. The tool description adds no additional parameter meaning, but the baseline is met since coverage is 100%.

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 produces a spend report for an agent with specific breakdowns (totals, by rail, by service, budget status, anomalies). It does not explicitly contrast with sibling tools, but the 'report' focus 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?

No guidance is provided on when to use this tool versus siblings like ledger_set_budget or ledger_track. The description does not mention prerequisites or alternative scenarios.

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?

The description only conveys that the tool modifies budget caps ('Set'). It does not disclose how missing parameters are handled (e.g., daily_cents defaults to 0), whether it overwrites or merges existing caps, or any side effects. With no annotations, the description carries the full burden and falls short.

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 concise and to the point, with no unnecessary words or jargon. It effectively communicates the core action in a single sentence.

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?

The description is adequate for a simple mutation but lacking in context. It does not mention the return value or output schema, even though one exists, nor does it explain expected behavior when certain parameters are omitted. This could leave an agent uncertain about the tool's full effect.

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?

All three parameters have descriptions that convey their basic meaning. Daily_cents clearly notes that 0 means no cap and has a default. However, monthly_cents lacks a similar clarification for 0, leaving possible ambiguity.

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: setting an agent's budget caps. It uses a specific verb-object structure and is distinct from sibling tools like ledger_alerts, ledger_report, and ledger_track.

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 no guidance on when to use this tool versus alternatives. It does not mention any conditions, prerequisites, or scenarios where this tool should or 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?

The description indicates a write operation ('Record') but does not disclose side effects such as whether it creates a new entry, updates an existing one, or is idempotent. With no annotations provided, the description carries the burden, but it remains minimal and does not fully specify behavioral expectations.

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, concise sentence that immediately states the purpose. It contains no redundant words or vague phrasing, making it highly efficient and well-structured.

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?

The description, combined with the detailed parameter schema, provides enough context for an agent to understand what the tool does. Since an output schema exists, the description need not explain return values. However, it omits any mention of edge cases or preconditions, which is a minor gap but does not hinder basic usage.

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 provides descriptions for all four parameters (agent_id, rail, amount_cents, service) with sufficient detail, including enum-like values for rail and an example for service. The description adds no extra semantic meaning beyond the schema, so it neither enhances nor detracts from the parameter clarity.

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 action ('Record') and the object ('a spend entry for an agent'). It unambiguously distinguishes this tool from siblings like ledger_report or ledger_set_budget by focusing on recording individual spend transactions.

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 no guidance on when to use this tool versus the sibling tools. It does not mention that this should be used for logging individual spend events, nor does it contrast with ledger_alerts or ledger_report. An agent would have to infer usage from the name and parameters alone.

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