AgentBroker Index

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

Annotations already declare readOnly, idempotent and closed-world, so the safety profile is covered. The description adds genuinely non-derivable behavior: output order mirrors input order and the result is explicitly not a ranking, which prevents a common misinterpretation. No detail on missing/unknown provider handling, but the added value is real.

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 that packs the scope, the compared dimensions and the key behavioral caveat with no filler. Every clause carries information an agent uses.

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 usefully enumerates what the comparison returns, which largely substitutes for return-value documentation. The undocumented lang parameter and lack of guidance on invalid or unknown ids keep it just short of 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?

Schema coverage is 0%, so the description must compensate. It explains the ids semantics (2-4 providers, order preserved), which maps directly to the minItems/maxItems and ordering behavior. The 'lang' parameter is never mentioned, and no id format or example is given, so compensation is partial.

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?

Specific verb+resource ('side-by-side comparison ... for 2-4 providers') plus the exact dimensions compared (capability, integrations, assistants, limits, Spain availability, licence, sources). It also implicitly separates itself from get_provider (one provider) by naming the multi-provider scope, so an agent can pick it without opening a schema.

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 cardinality constraint (2-4) implies when this tool applies, and 'this is not a ranking' warns against misreading output, but the description never names get_provider or search_providers as alternatives or states the condition for choosing comparison over a single lookup.

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 establish that this is a safe, read-only, idempotent, closed-world operation, so the safety profile is covered. The description adds value by naming the specific fields returned (licence, attribution, methodology page), which matters because no output schema exists, but it says nothing about response shape, freshness semantics of the 'last full check date', or whether the links are absolute.

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 compact sentence with no filler, and the most decision-relevant content (counts, licence) is front-loaded. It is a fragment rather than a well-formed statement, which slightly weakens readability without wasting 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?

For a zero-parameter, read-only tool with annotations covering safety and no output schema, the description does the important remaining work by listing the return contents. It omits scope (dataset-wide vs. per-provider) and freshness caveats, keeping it short of 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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter-level claims are made or 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 enumerates what the tool surfaces (counts, check date, licence, attribution, download links, methodology) which lets an agent infer it returns dataset-level metadata. However, it is a bare noun phrase with no verb, and it makes no attempt to distinguish itself from siblings such as get_provider or search_providers. Purpose is inferable but not stated.

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?

There is no guidance on when to call this versus the sibling tools, and no prerequisites or exclusions are mentioned. The agent must guess that this is the entry point for corpus-wide metadata rather than provider-level detail.

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 establish that this is a read-only, idempotent, non-open-world lookup. The description adds useful behavioral context about the returned data itself: it is sourced, includes source URLs and check dates, documented limits and approvals, legal entity and licence status in Spain, and availability by market. It does not cover error behavior or auth, but for a read-only lookup the added sourcing and content detail is substantive.

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, front-loaded sentence that efficiently lists the entry's contents. The long parenthetical field list is dense but every item conveys what the agent will receive, and there is no filler or repetition.

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?

Because there is no output schema, the description appropriately carries the burden of explaining what the tool returns, and it does so extensively. It is nearly complete for a read-only full-record lookup, with the main remaining gap being explicit routing guidance versus sibling tools rather than return-value explanation.

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 does not mention either parameter. The schema describes 'id' well with examples, but the other parameter, 'lang', has only an enum and default with no explanation, and the description does nothing to clarify whether it controls response language or filtering. With 50% schema description coverage and no compensating parameter detail in the description, this is a clear gap.

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 resource: the 'Full AgentBroker Index entry for one provider', and enumerates the entry's contents. It is specific enough to distinguish a full single-provider lookup from list/compare/search siblings, though it does not explicitly name those siblings or state that this is the detailed-record retrieval tool.

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 phrase 'for one provider' implies usage when the agent already has a provider identifier and needs the complete record. However, there is no explicit guidance on when to use this instead of search_providers, compare_providers, or list_changes, and no stated exclusions or prerequisites.

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 establish readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so the safety profile is covered. The description adds that entries are dated and each carries a source URL, which is genuinely useful return-content context absent from any output schema, but it omits ordering (newest-first?), whether the default limit of 15 truncates silently, and whether pagination exists.

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, zero filler, with the core resource identity and payload front-loaded before the filtering note. Nothing in it is redundant.

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 read-only list tool with no required parameters and strong annotation coverage, the description is close to sufficient, and the lack of an output schema is partly offset by the source-URL note. It still leaves ordering, default-limit behavior, and the role of the 'lang' parameter unexplained, which matters for correct invocation.

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 exactly 50% — 'since' (YYYY-MM-DD) and 'provider' are documented inline, while 'lang' and 'limit' rely on enum/default/min-max alone. The description's 'Filter by date or provider' maps to the two documented parameters but adds no format or semantics beyond what the schema already says, and says nothing about 'lang'.

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 gives a concrete verb+resource combination — a dated changelog of launches and changes — and enumerates the content types (new MCP servers, connectors, permission changes) plus the source URL payload. It is clearly a different resource from the sibling provider tools (compare_providers, get_provider, search_providers), though it never names them explicitly to reinforce the distinction.

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?

'Filter by date or provider' implies the intended usage pattern, but there is no explicit when-to-use guidance, no exclusions, and no routing to alternatives. An agent can infer this is the changelog-retrieval tool, but must guess whether e.g. search_providers should be used when looking for a specific provider's entry.

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, idempotentHint and openWorldHint=false. The description adds value beyond them by disclosing what comes back ("sourced, dated summaries" — provenance and recency) and the advisory boundary ("information, not advice"). It omits practical traits like default result count, the 25-result cap, and any paging behavior.

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 sentences, front-loaded with the verb and resource, then the filter axes and the return/disclaimer note. The long parenthetical enumerations are dense but every item corresponds to a real filter, so the length is functional rather than padding.

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 exists, so the description usefully characterizes the return as sourced and dated summaries. For a 10-parameter read-only search tool with strong annotation coverage and 70% schema descriptions, this is close to sufficient; only result-cap/limit behavior and the language parameter are left unexplained.

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 70% schema coverage across 10 parameters, the description meaningfully maps description-level vocabulary onto parameters: the capability enumeration ("place orders, draft orders, read only, none") matches the capability enum exactly, and "Spain availability/licence" covers both Spain booleans. It leaves lang, limit and official_only unaddressed, which is the remaining gap.

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 ("Find providers in the AgentBroker Index") and immediately enumerates the dimensions searched: name, type, agent capability, assistant, tradable asset, and Spain availability/licence. An agent can tell this is the broad lookup/list tool rather than the comparison or single-record 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 implied by the enumerated filter axes and the closing "Read-only; information, not advice," giving a clear sense of the legitimate context. However, it never names alternatives such as compare_providers or get_provider, nor states when-not to use it (e.g. for a single known provider or for head-to-head comparison).

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