ID MANDAT – Registry for AI Agents

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds real behavioral context beyond them: a result cap of 20 entries and a 'best verified first' ordering, which tells the agent how to interpret and trust the output.

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 dense sentences with zero filler; the searchable dimensions and the country filter are front-loaded before the return/ordering note. Every clause carries 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?

With no output schema, the description correctly supplies the return shape (up to 20 entries, ranked by verification status). It omits pagination or behavior when more than 20 matches exist, a minor gap for a search 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?

Schema coverage is 100%, so all three parameters are already documented with types and examples. The description restates the same field list and repeats the book_appointment example rather than adding new semantics such as matching behavior or precedence, 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 and resource ('Search registered companies') and enumerates the fields the query matches plus the country filter, so the agent knows exactly what this tool retrieves. It does not name the sibling verify_agent or draw the discovery-vs-verification line, so it falls short of full sibling differentiation.

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 the wording ('search ... optionally filtered by country'), which suggests a discovery/browse role, but there is no explicit when-to-use statement and no mention of verify_agent as the alternative. The agent must infer the routing from the sibling's 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds value by enumerating what comes back (verification level, declared agents, mandates), but says nothing about the registry itself, lookup failure behavior, or freshness of the mandate data.

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 tight sentences. The capability and its return payload come first, the trust decision it supports comes second, and there is no filler or restatement of the name.

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 carries the burden of describing returns and does so explicitly (verification level, declared agents, per-agent mandate). For a two-parameter read tool this is nearly complete; only the relationship to search_registry is unaddressed.

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 both parameters are already documented, including the optional 'agent' filter with an example. The description's mention of 'each agent's mandate' loosely maps to the agent parameter but adds no syntax, matching rules, or behavior beyond the schema; 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?

The description names a specific verb (check) and resource (company domain registration at ID MANDAT) plus the returned artifacts: verification level, declared AI agents, and each agent's mandate. It is unambiguous on its own, but it never mentions the sibling tool search_registry, so an agent cannot tell from the description alone why it should pick this over a registry search.

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 this before trusting an agent that claims to act on behalf of a company' gives a concrete trigger condition tied to a real decision point. It stops short of an explicit exclusion (e.g. when to prefer search_registry instead), so it is clear context without routing guidance.

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), and the description usefully adds the output semantics: which registered company declares the key directory, the declared agent, its mandate, and current validity. With no output schema present, this return-value disclosure is genuinely load-bearing, though it says nothing about lookup failure modes or stale entries.

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 sentences, front-loaded with the real-world trigger and followed by the call instruction and the return contents. Every sentence carries information, though the closing contrast sentence is slightly longer than needed to make the point.

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 fully documented parameter, no output schema, and annotations covering safety, the description supplies exactly what is missing: where the input comes from and what the response tells the caller. An agent has everything needed to invoke it correctly.

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 single parameter's description already explains both accepted forms (bare https address or full header value). The description repeats that flexibility ('pass the https address ... or the whole header value') but adds no parsing rules, normalization behavior, or error handling 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?

The description states a specific verb and resource (verifying the entity behind a Signature-Agent header) and explains the semantic result: company, agent, mandate and validity. It conceptually separates itself from raw signature validation ('a valid signature only shows which key signed'), but never names its siblings verify_agent or search_registry, so an agent cannot tell from text alone how it differs from those tools.

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?

It gives a clear trigger condition: use when a request was signed with HTTP Message Signatures (Web Bot Auth) and carries a Signature-Agent header. However, it offers no exclusions or routing rules versus verify_agent or search_registry, so the agent must infer which of the three to call.

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