taxcredit-engine

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

With no annotations, the description carries full burden. It discloses that missing facts return indeterminate and provides a disclaimer that it's not tax or filing advice. It also mentions pricing and payment flow. However, it does not describe side effects, authorization needs, or rate limits beyond cost. Behavioral traits beyond what is stated are missing.

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 somewhat lengthy due to pricing and payment details, but front-loads the purpose. It could be more concise by separating operational info (pricing) from functional description. Each sentence adds value, but the structure mixes core function with payment instructions.

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 an output schema exists, the description does not need to explain return values. It covers credit types, fact requirements, and pricing. However, it lacks details on what 'auditable' means and the expected structure of the output. The description is adequate but not thorough for a tool with no 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?

Schema coverage is 0%, so description must add meaning. It specifies that 'credit' can be '45Q, 45V, 45Y, 48E, or 45X' and that 'facts must contain the explicit credit-specific eligibility facts'. It also hints at 'payment_ref' in pricing. This adds significant value beyond the bare schema, though the structure of 'facts' remains vague.

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: 'Calculate an auditable tax-credit scenario.' It lists the specific credit types (45Q, 45V, 45Y, 48E, 45X), which distinguishes it from sibling tools like verify_tax_credit_result that handle verification. The verb 'Calculate' and resource 'tax-credit scenario' are precise.

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 notes that 'missing facts return indeterminate' and provides pricing and payment instructions, but lacks explicit guidance on when to use this tool vs siblings like get_rule_pack or verify_tax_credit_result. No 'when not to use' or alternative recommendations are given.

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 burden of disclosing behavior. 'Return' implies a read-only operation, but it does not explicitly confirm no side effects, auth requirements, or rate limits. The transparency is minimal but not misleading.

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 sentence with no unnecessary words. It is front-loaded with the verb 'Return'. Every word contributes meaning, making it highly concise.

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 0 parameters and the presence of an output schema, the description is largely sufficient. It covers the key output aspects (capabilities, version, pricing). However, it could briefly clarify what 'fleet-standard' means or that the tool is safe to call without side effects.

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 0 parameters, so the schema coverage is trivial (100%). According to the rule, baseline is 4. The description adds purpose beyond the empty schema, justifying a 4.

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 'Return fleet-standard capabilities, version, and pricing' clearly states the verb (Return) and the resource (fleet-standard capabilities, version, pricing). It distinguishes itself from sibling tools like calculate_tax_credit and get_rule_pack, which deal with different domains.

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 does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or contexts. Usage is implied by the tool's purpose, but no direct guidance is given.

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 must fully disclose behavior. It states 'Return,' implying a read-only operation, but lacks details on side effects, authorization needs, rate limits, or error handling (e.g., invalid credit). 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 sentence with no fluff, achieving conciseness. However, it is too brief to be adequately structured; it could be rephrased to front-load the key action while adding brief parameter context.

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?

Despite having an output schema, the description does not elaborate on return content (e.g., rule structure or metadata fields). With one parameter, the description should minimally explain the parameter's role, which it fails to do, making the tool incomplete for reliable agent use.

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 tool description does not explain the 'credit' parameter beyond its name. The agent has no indication of whether credit is an ID, name, or code, nor any format constraints. This is a critical gap for correct usage.

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 returns 'bundled rules and official source metadata for one credit,' with a specific verb and resource. This purpose distinguishes it from siblings like list_rule_packs (which likely returns multiple credits) and calculate_tax_credit (which involves computation).

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 on when to use this tool versus other siblings. The description does not mention scenarios, prerequisites, or alternatives (e.g., 'use list_rule_packs to see all credits'). This leaves the agent without context for appropriate invocation.

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 discloses the output (credits and digest) but does not mention whether the tool is read-only, requires authentication, or has any side effects. Since no annotations exist, the description carries full burden, and it is minimally adequate.

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, clear sentence with no redundancy or extraneous information. Every word is meaningful and 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 list tool with no parameters and an output schema (presumably defining return fields), the description covers the essential purpose. It could mention that it is safe to call repeatedly, but it is sufficiently complete given the tool's simplicity.

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 has zero parameters, so schema description coverage is effectively 100%. There is nothing for the description to add regarding parameters, earning a baseline score of 4.

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 it lists 'supported credits' and 'current bundled rule-pack digest,' which defines its output. However, it does not explicitly distinguish itself from the sibling tool 'get_rule_pack,' but the verb 'list' implies a collection retrieval rather than a single item.

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 alternatives like 'get_rule_pack'. There is no mention of prerequisites, limitations, or exclusions, leaving the agent to infer usage from the tool name.

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 full burden. It discloses that changes in amount, fact, rule step, or source digest cause failure, providing some behavioral insight. However, it does not mention return format, side effects, or whether it is idempotent. The output schema likely covers some of this, but description itself is moderately 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?

The description is two sentences, front-loads the action, and contains no superfluous words. Every sentence provides essential 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 simplicity (one parameter, output schema exists), the description is fairly complete. It explains what to pass and the failure condition. Missing minor details like exact output on success, but output schema likely covers that.

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. It adds that the parameter should be a JSON string of the prior result, but does not detail expected structure or fields. Parameter name 'result_json' already hints at JSON, so description adds minimal meaning beyond that.

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: verifying audit_sha256 of an engine result. It uses a specific verb 'verify' and resource, and it clearly distinguishes from sibling tools which are about calculations, descriptions, or rule packs.

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 clear context on usage: pass the prior result object as JSON and that any change in specified fields causes failure. It implicitly tells when to use (after obtaining a prior result), but does not explicitly state when not to use or mention alternatives.

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