bridge

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

Annotations declare non-readonly, openWorld, non-idempotent, non-destructive, but the description adds material context the annotations cannot: the spec is fetched over the network, tools are stored UNEXPOSED, and nothing is callable until a human publishes. It stops short of warning that repeat calls create additional draft servers.

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?

Front-loaded with the core action, then a short rationale paragraph, then the return summary and the when-to-use line. The 'that is deliberate' sentence is slightly editorial but carries real behavioral intent, so the length is defensible.

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, yet the description states exactly what comes back (server id, proposed tools with HTTP methods, console link), which is what an agent needs to proceed. Combined with the draft-state caveat, 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 description coverage is 100%, so both parameters (name, source_url) are already documented with format and constraints (public HTTPS, no credentials). The description restates the public-URL requirement without adding syntax 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 (Turn ... into) and resource (a DRAFT MCP server from an OpenAPI spec) and explicitly scopes the outcome as a non-published draft. An agent can distinguish this from get_server/list_my_servers/reintrospect_server purely from the description.

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?

Ends with explicit when-to-use guidance ('Use when someone wants to give an agent access to an API they have a spec for') and clarifies a key exclusion — this tool cannot publish. It does not name a sibling alternative, so it stops short of full 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 declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: tools are NOT exposed by default, this returns a proposal, and a human publishes it via console_url — which materially shapes how an agent should interpret the result.

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 with the return contents front-loaded, then usage, then the key caveat about publication. Every sentence carries weight, though the final sentence about console_url largely restates 'a human publishes it in the console' with only a field name added.

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 must carry the return-value burden, and it does enumerate the meaningful fields plus the console_url. For a single-parameter read tool with full annotation coverage, an agent has enough to call it and interpret the result; only the sibling-tool boundary with reintrospect_server is left 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 the single server_id parameter is already fully documented including where to obtain it (list_my_servers or create_server). The description adds no format, constraint, or edge-case detail beyond the schema, 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?

States a specific verb and resource ('Show one server') and enumerates exactly what comes back: proposed tools, exposure status, state, gateway URL. That enumeration plus 'one server' implicitly separates it from list_my_servers. It does not, however, distinguish itself from reintrospect_server, so the sibling separation is only partial.

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 explicit usage contexts: 'after create_server to see what was discovered, or when deciding which tools to expose,' which is clear when-to-use guidance naming a sibling. It stops short of stating when to prefer reintrospect_server or list_my_servers instead, so there is no exclusion 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 declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds real value beyond that by enumerating the returned fields (name, slug, draft/live state, proposed vs exposed tool counts, gateway URL once live), which compensates for the absent output schema.

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 what, then the return payload, then the usage triggers. No redundant restatement of the title and 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?

For a zero-parameter, read-only listing tool with no output schema, the description supplies exactly the missing piece — the shape of what comes back — plus the workflow context. An agent has everything needed to call it correctly and interpret the result.

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 per the rubric this is the baseline 4. There is nothing for the description to disambiguate, and it correctly avoids inventing filter or pagination arguments.

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 (list) and resource (MCP servers in your Kaiva Bridge workspace), and immediately scopes the result set to the caller's own workspace. The sibling set (get_server, reintrospect_server, create_server) is implicitly distinguished: this is the enumeration entry point, not the single-resource read or the mutation.

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 concrete when-to-use conditions: find a server before inspecting or re-introspecting it, or answer "what have I built". It routes the agent toward the correct workflow without explicitly naming get_server/reintrospect_server as the follow-on calls or stating any exclusions.

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 adds substantial behavioral nuance beyond the annotations: existing tools keep exposure, new operations arrive UNEXPOSED, and removed operations disappear. This aligns with idempotentHint and destructiveHint while conveying the opt-in policy that annotations alone 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 four sentences, each carrying essential information: purpose, stability guarantee, opt-in behavior, and usage trigger. It is front-loaded and contains 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 one fully documented parameter and annotations covering idempotency and destructiveness, the description supplies the missing context: when to call it and exactly what happens to existing, new, and removed tool definitions. It is complete enough for an agent to select and invoke the 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?

The input schema fully documents the only parameter, server_id, with 'The server id to refresh.' The description does not add extra semantic detail beyond that, so the baseline of 3 is appropriate.

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 opens with a specific action and resource: 'Re-read a server's source spec and refresh its tool list.' It clearly distinguishes this from the sibling tools create_server, get_server, and list_my_servers by focusing on refreshing after upstream changes.

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 explicit triggers: 'Use when an API has shipped new endpoints, or when a server's tools look out of date.' It also explains the safety semantics around existing and new tools, but it does not explicitly state when not to use it or directly compare against alternatives.

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