AgentDNA by ANGELS

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

Annotations already declare readOnlyHint, idempotentHint, and closed-world behavior, so the safety profile is covered. The description adds real context beyond them: it discloses the actual content payload (free trial duration, exact price, publishing steps) and confirms 'No input', which tells the agent this is a static informational call.

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 delivering subject, contents, and the no-argument fact with zero filler. Every clause 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 zero-param, no-output informational tool this covers what the agent needs. A minor gap is not indicating whether the pricing/steps content is authoritative or static, but nothing required 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?

With zero parameters, the baseline is 4, and the description explicitly states 'No input', removing any ambiguity about whether arguments are expected. Nothing further is needed.

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 resource (AgentDNA, its pricing, and the publishing steps) with the verb 'explains', making the informational nature unambiguous. It is clearly distinguishable from sibling action tools like agentdna_start_trial and agentdna_search_products.

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 scope (company catalogs for AI agents, price, publishing steps) implies the natural use case: answering orientation/pricing/onboarding questions before invoking the action tools. It does not explicitly say 'call this before start_trial' or name exclusions, which keeps it below a 5.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description earns credit for disclosing the shape of the returned payload (products, prices, availability, contact), which matters because there is no output schema; it does not cover catalog size or pagination.

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 resource, contents, and lookup key; nothing redundant or padded.

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 one well-documented parameter, rich read-only annotations, and no output schema, the description supplies the one thing structured data lacks: the contents of the returned catalog. Only the absence of any size/volume expectation keeps it short of full.

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 100% and the schema already gives the format hint ('no https://') with an example. The description's 'by its domain' adds nothing 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 verb ('Returns') and resource ('a company's full AgentDNA catalog'), and enumerates the payload (products, prices, availability, contact) plus the lookup key (domain). It implicitly distinguishes itself from agentdna_list_companies and agentdna_search_products by promising the complete record for one company, but it never names those 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?

Usage is only implied: 'by its domain' suggests you need a known domain and want everything at once, but there is no explicit statement of when to prefer this over agentdna_search_products or agentdna_list_companies, and no mention of failure behavior for unknown domains.

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 readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuine value beyond that by disclosing the filtering rule ('live' catalogs only) and the shape of each record. It says nothing about pagination, total counts, or what happens when no results exist.

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?

One sentence, front-loaded with the verb and resource, zero filler. Every clause (live filter, returned fields) 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?

With no output schema, the description does list the returned fields, which helps. But for a list tool it omits anything about result ordering, truncation at the limit, or whether more results can be fetched, leaving an agent unable to reason about completeness of the result set.

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%: the single 'limit' parameter is fully documented with range and default in the schema. The description adds no parameter-level detail, so 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 verb+resource ('Lists the companies') and adds the qualifying scope 'that publish a live AgentDNA catalog', plus the fields returned (verified status, product count, catalog URL). It's clear what the tool does, but it never contrasts itself with siblings like agentdna_search_products or agentdna_get_catalog, so differentiation is left to the name.

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 when-to-use, when-not-to-use, or alternative routing is given. An agent must infer from the name alone that this is the discovery entry point before calling agentdna_get_catalog or agentdna_search_products; the description offers no guidance on that sequence.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds useful scope ('across every live AgentDNA catalog') and return contents ('company, price and availability'), which is valuable extra context. It does not describe ranking or pagination behavior, but that is minor for a read-only search.

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 zero filler; the scope and return values are front-loaded. Every clause 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 two-parameter search tool with full schema coverage and read-only annotations, the description is sufficient: it states scope, backend coverage, and what matches include. No output schema exists, so mentioning return fields is valuable; nothing essential 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?

Schema coverage is 100%, so the schema fully documents both query and limit. The description does not add any parameter semantics beyond the schema's own descriptions (e.g., examples or defaults), so the baseline of 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?

The verb 'Searches' and resource 'product names and descriptions across every live AgentDNA catalog' are specific and unambiguous. It distinguishes itself from catalog-metadata tools by focusing on product search across all catalogs, though it does not explicitly name a 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?

No explicit when-to-use guidance or exclusions are given; the agent must infer from the name and scope that this is the product search tool. It does not mention when to use agentdna_get_catalog or agentdna_list_companies instead.

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?

Adds meaningful context beyond the annotations: the API key is disclosed only once and cannot be re-read, the trial is free for 30 days with no card, and the catalog is unverified until domain proof. These are exactly the facts an agent needs before committing. It stops short of covering repeat-invocation behavior, which matters since idempotentHint=false and no guidance is given on what happens if a catalog already exists for the domain.

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 sentences, front-loaded with the action and return value, then eligibility, then the verification caveat. No filler and nothing repeated from the schema or annotations.

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?

Covers the critical gaps for a creation tool with no output schema: what is returned (key plus next steps), its one-time visibility, and the trial terms. The remaining omission is repeat-call semantics for a non-idempotent operation on the same domain, which an agent would want before retrying.

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 four parameters are already documented in the schema, establishing a baseline of 3. The description adds only indirect meaning — the domain-verification sentence hints at why the domain parameter matters — but gives no format, validation, or edge-case detail beyond the schema.

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 and resource ("Creates an AgentDNA catalog for a company") and immediately names what it returns (private API key plus next steps). This is clearly distinguishable from siblings like agentdna_get_catalog, agentdna_list_companies, and agentdna_search_products, which are all read-side operations.

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?

Provides a real eligibility gate — "Use only for a company you act for" — and explains the consequence path (catalog stays unverified until the domain owner proves ownership). It does not explicitly name an alternative tool for cases where the agent should not start a trial, but the sibling set makes the read-vs-create split obvious.

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