AgentBridge — Discover A2A Services from MCP

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

With no annotations, the description carries the full burden and does add important behavioral context: descriptors are untrusted data, not instructions, and discovery does not pay or execute. This clarifies safety and side-effect expectations, though it omits details like authentication, rate limits, or whether the operation is read-only.

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 tightly written sentences: the first front-loads the purpose, the second adds a critical safety note. Every sentence earns its place with no redundancy.

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 discovery tool with no output schema, the description is mostly complete: it states the scope and cautions about untrusted data. It could elaborate slightly on what 'capabilities' or 'declared HTTP resources' entail, but no critical information is missing 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?

The tool has zero parameters, so per the rubric the baseline is 4. The description does not need to explain parameter meanings, and the schema confirms no inputs.

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 'Discover' and names the resource: 'capabilities on the other agent protocol and declared HTTP resources.' It is clear enough for an agent to understand the tool's function, though the phrase 'other agent protocol' remains somewhat abstract. No sibling tools exist, so sibling differentiation is not applicable.

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 states what the tool does but gives no explicit when-to-use guidance, no prerequisites, and no alternatives. An agent must infer that this tool is for capability discovery, but there is no context about when to invoke it versus other actions.

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 at all, the description carries the full burden, and it does disclose two meaningful traits: requestKey provides idempotency, and uncertain calls are never automatically retried (implying side effects and that the agent must follow up via execution_status). However, it says nothing about what the call mutates, what permissions are needed, what gets returned, or what 'uncertain' means operationally.

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 short sentences with no filler, and the idempotency instruction is front-loaded after the purpose statement. The terseness comes at the cost of clarity around 'other protocol', but there is no 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?

This is a high-complexity tool: four parameters, a nested sourceCheck object, no annotations, and no output schema. Two sentences cannot cover the shape of 'arguments', how contractId is sourced, or what a caller should do after an uncertain failure — all of which the description would need to supply.

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 only 25% — only sourceCheck is documented. The description adds real meaning for requestKey (must be stable) but leaves contractId and the free-form arguments object completely unexplained, so three of four parameters lack semantic guidance in either source.

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 'Execute' is clear and the object is broadly named ('a pinned capability on the other protocol'), but 'other protocol' and 'pinned capability' are undefined jargon. It does not distinguish itself from siblings like discover or execution_status, so an agent must infer that this is the invocation step of a discover → execute → status workflow.

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 an implementation instruction ('use a stable requestKey') and a caveat about retries, but never states when to call this versus execution_status or how to obtain a contractId (presumably via discover). No explicit when-to-use or when-not-to-use guidance is offered.

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 carry the full behavioral burden, and it does disclose something genuinely non-obvious: refresh uses GetTask and is strictly non-repeating, distinguishing it from a re-execution. It does not state what happens if the requestKey is unknown/expired, whether the outcome is durable indefinitely, or what the read returns.

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 with no filler; the core purpose is front-loaded and the refresh caveat follows immediately. 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?

There is no output schema, so the description should convey what an agent receives back (status vs. result vs. task state), and it does not. It covers the read semantics and the refresh flag adequately but leaves the return contract and error behavior unstated.

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 gives real meaning to the optional refresh flag (reads an existing A2A task via GetTask, no re-send), but says nothing about requestKey, the required parameter, which is left entirely to its name and maxLength constraint.

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: "Read the durable execution outcome." It implicitly differentiates from the sibling execute by asserting it never re-runs the work ("never repeats SendMessage or tools/call"), though it never names the siblings discover or execute directly.

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 refresh wording implies this is a polling/status check on a previously issued request and that refresh is for re-reading an existing A2A task, which is useful conditional guidance. However, there is no explicit statement of when to call this versus execute, or when refresh should be left off beyond "optional."

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 the full behavioral burden and does so well: it discloses that only suggestions and declared prices are returned, that relevance is not guaranteed, that it is an identity-free public guest trial, that requestKey does not alter the shared argument-keyed cache, and that guest execution_status is unavailable.

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?

Purpose is front-loaded in the first sentence and the following sentences are dense with distinct caveats. Some clauses are telegraphic and cryptic, e.g. 'Preserve arguments after uncertainty,' which costs clarity without obvious payoff.

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 tool with no output schema and a nested object parameter, the description is fairly complete, covering return shape, pricing caveat, identity model, caching, and a key limitation. It stops short of describing the 'text' argument's expected content or format.

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 50%, and the description adds real value for requestKey by explaining it is optional and does not change the cache key. However, the primary 'arguments.text' field is only hinted at via the PDF example, so the main input's semantics remain largely undocumented.

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 (ask for recommendations) and resource (document conversion or web utility recommendations), with a concrete example. It implicitly distinguishes itself from the 'execute' sibling by stating it 'does not run or buy suggested tools,' though it never names that sibling directly.

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?

Clear context: use this for provider/price recommendations, and explicitly not for running or buying tools, which routes the agent toward 'execute'. It does not name alternative siblings like 'discover' or 'execute' by name, so the routing is inferred rather than spelled out.

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 the full burden and does so well: it discloses that output is provider-generated with references 'when available', warns to verify claims, notes the guest trial has no identity, that guest execution_status is unavailable, and that requestKey does not alter the shared cache. These are non-obvious behavioral traits an agent needs.

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 purpose is front-loaded, but several trailing sentences are cryptic and under-explained ('Guest execution_status is unavailable.', 'Preserve arguments after uncertainty.'), which cost clarity without clearly earning their place in a short definition.

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 nested-argument tool with no output schema, the description covers return content (provider-generated explanation with references), security boundaries, caching semantics, and guest limitations. It is close to complete, missing only explicit sibling differentiation.

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 only 50% (only requestKey is documented in-schema), so the description compensates by specifying repoName format ('owner/repository') and clarifying requestKey's optionality and caching behavior. The 'question' parameter is left only to its name and maxLength, which is a minor 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 ('Ask a bounded question') and resource ('one public GitHub repository indexed by DeepWiki'), making the operation clear. It does not explicitly distinguish itself from the sibling free_deepwiki-public-structure tool, so an agent must infer the difference between asking a question versus retrieving structure.

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 context (public repo, bounded question, guest trial) but never names alternatives or states when-not to use it versus free_deepwiki-public-structure or free_agenthub-free-guidance. The security constraint ('Never send private code or secrets') is helpful but is a restriction, not 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?

With no annotations, the description carries the full burden and does disclose meaningful traits: guest/trial mode with no identity, requestKey not affecting the shared cache keyed by public arguments, and execution_status being unavailable for guests. It omits any error, rate-limit, or failure-mode detail, but the caching and auth disclosures are real added value.

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?

Purpose and the repoName format are front-loaded, and each subsequent sentence carries behavioral information rather than filler. The closing 'Preserve arguments after uncertainty' is terse and slightly cryptic, costing a point on structure.

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?

There is no output schema, yet the return is described only as 'topics, not source files or a general answer' — an agent gets no sense of the shape or granularity of a topic structure. Auth and caching are covered, but return-format detail and failure behavior are left incomplete for a tool with a nested argument object and zero 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 only 50% (repoName has no schema description), and the description compensates by giving the required format and an example, 'owner/repository, e.g. microsoft/TypeScript.' It also explains requestKey's optionality and its non-effect on the cache key, adding semantics beyond the schema's pattern/description.

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: 'Read the documentation topic structure for a public GitHub repository indexed by DeepWiki.' It further disambiguates from the sibling question tool with 'Returns topics, not source files or a general answer,' so an agent can separate this from free_deepwiki-public-question without opening either 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?

Gives clear context ('Public guest trial without identity', 'Guest execution_status is unavailable') and implies the when-not case by contrasting the return type with a general answer. It never names an alternative sibling explicitly, so it lands at clear-context-without-explicit-alternatives rather than a 5.

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