Neuronto Agentic Resource Discovery (ARD) Index

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, and the description adds material behavior the annotations cannot convey: the federated live query to upstream registries, ranked fusion, the fact that the returned score is relevance only and not a trust or safety signal, and that payment terms come from the publisher manifest or the endpoint's own 402 with the caller paying the provider directly.

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 what the tool does and immediately followed by the return shape and a critical caveat about the score's meaning. Dense but every sentence carries distinct information; no filler.

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 return-shape burden and does it: ranked matches, relevance score, endpoint to connect to, and which registries carry each result. Combined with payment-term provenance, an agent has enough to call and interpret this tool 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 86%, so the baseline is 3, but the description adds real semantic depth the schema lacks: the distinction between 'free' (none known) and 'payable' (price or 402 known), the source of price terms, and direct caller-to-provider payment. It says nothing about 'kind', 'limit', 'federate' or 'network' 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 ('Search for an MCP server, skill, agent, API or other callable capability for a task') and precisely scopes it ('across this index and every other public ARD registry at once'). It never names or contrasts the sibling find_tool, so an agent must infer the split between the two finders.

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 rather than stated: the description covers payment filtering and price caps, suggesting when those filters matter, but gives no explicit guidance on when to use this over find_tool or registry_stats. No prerequisites or exclusions are named.

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 destructiveHint false. The description adds valuable behavioral context: results are read back from a live server's tools/list, so names and schemas are what the server actually exposes rather than what descriptions claim. This goes beyond the annotations without contradicting them.

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 focused sentences with no filler. The primary purpose and verification behavior are front-loaded, and the sibling differentiation is placed exactly where it is most useful.

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 read-only search tool with rich annotations and a schema that covers the parameters, the description is largely complete. It explains what results are and how they are sourced, though it does not specify the exact return shape or fields when with_schema is false; this is a minor gap 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?

Schema description coverage is 67%, and the schema already documents query and with_schema. The description reinforces query semantics with 'by name and behaviour' and explains with_schema's purpose, but it does not add meaningful detail about the limit parameter beyond what the schema's min/max/default already communicates.

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 uses a specific verb ('Search') and resource ('individual MCP tools by name and behaviour'), and explicitly distinguishes itself from searching by server. It also clearly differentiates from the sibling find_resource by naming the exact alternative condition.

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 explicit guidance: use this tool when you know the shape of the call you need, and use find_resource when looking for a service. This is direct, actionable routing guidance that leaves little to inference.

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 goes well beyond the annotations by disclosing the verification behavior: an endpoint 'must complete an MCP initialize handshake' and a domain 'must serve a manifest that parses.' It also reassures the agent that 'nothing is taken on trust,' adding meaningful operational context that the annotations do not provide.

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 three sentences with no filler. The primary purpose is front-loaded, the parameter mapping is compact, and the verification behavior earns its place. Every sentence contributes useful 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?

For a low-complexity tool with two fully documented parameters and helpful annotations, the description covers purpose, parameter selection, and verification. It does not describe the response/error format, and there is no output schema to fall back on, which is a minor completeness gap.

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 baseline is 3. The description adds value by pairing each parameter with its intended usage and validation requirement, clarifying that endpoint means an MCP server URL and domain means a site serving an ARD manifest. This goes beyond the schema but could have specified the either/or selection rule more explicitly.

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: 'List an MCP server or an ARD-publishing domain in this index so other agents can discover it.' It clearly distinguishes the publish/registration intent from the sibling find tools, and the two supported forms (endpoint vs domain) are explicit.

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 concrete guidance on which input to provide: 'Give `endpoint` for an MCP server URL, or `domain` for a site that serves an ARD manifest.' It implies this tool is for registering resources rather than discovering them, but it does not explicitly name alternatives or say when not to use it.

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 mark the tool as read-only, idempotent, and non-destructive. The description adds meaningful behavioral context by specifying what the statistics cover and the concept of introspection verification. No side-effect or return-format disclosure, but annotations cover the safety profile.

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 that packs four distinct aspects of the statistics without redundancy. It is front-loaded with 'How large this index is' and avoids filler.

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 parameterless read-only stats tool, the description covers what the operation tells you. There is no output schema, so a structured return format isn't specified, but the listed categories are sufficient for an agent to understand the tool's value. Minor gap: no explicit statement of the output representation.

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 the schema is trivial. Per the baseline for parameterless tools, the description is not required to elaborate parameter semantics.

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 the exact content of the statistics (size, contents, verification, federated registries), which makes the tool's purpose identifiable. It lacks an explicit action verb like 'return' or 'show', but the title and description together clearly indicate a stats/inspection tool, and it is distinct from the find_* 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?

The description implies the tool is for retrieving index statistics, but does not state when to use it in preference to find_resource/find_tool, nor any exclusions. The purpose difference is obvious enough that an agent can infer usage, but explicit guidance is absent.

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