Siglume MCP Gateway

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context beyond annotations: 'This never discovers, meters, or contacts the provider.' This clarifies that the tool is purely local and non-intrusive, which is not conveyed by the annotations alone. No contradiction; the description enriches the read-only 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?

The description is extremely concise: two sentences that immediately state the action and the key constraint (no provider contact). There is zero fluff, and the critical scoping information is front-loaded. Every word contributes value.

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 a single parameter and no output schema, the description provides the essential context: what it reads, the prerequisite (active server), and what it does not do (discover/meter/contact). It does not explain the return format, but given the simplicity and annotations covering safety, the description is sufficiently complete for an agent to call 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?

With schema description coverage at 0%, the description must compensate for the single parameter 'server_id'. The description implies server_id identifies an 'already-active MCP Router server,' giving some context. However, it does not specify what constitutes an active server, how to obtain a valid ID, or any format expectations. It adds partial meaning but leaves gaps.

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 states a specific verb ('Read') and resource ('canonical cached tools for an already-active MCP Router server'). It explicitly distinguishes from discovery by saying 'never discovers, meters, or contacts the provider,' which differentiates it from sibling mcp_router_search. The purpose is unambiguous.

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 specifies the condition for use: the server must be 'already-active' and it emphasizes the tool never contacts the provider, implying it is for offline inspection. However, it does not explicitly contrast with the sibling mcp_router_search or state when to prefer this over search. The context is clear but lacks explicit 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?

Annotations already declare readOnlyHint=true, so no safety disclaimer is needed here. The description adds useful scoping context ('only external...') and an explicit exclusion of API Store coverage, but it does not disclose response shape, pagination, or error behavior. This is comparable to a safe read-only search tool where the core behavioral requirement is already annotated.

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, no filler, with the scope constraint front-loaded before the routing guidance. Every sentence earns its place and the alternative tool is introduced efficiently.

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 search tool with no output schema, the description covers scope, limitation, and routing to the correct alternative. It is slightly incomplete on query/limit semantics, but the parameter names and the tool title make those reasonably self-evident, and annotations cover the safety profile.

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 33%, and the description adds no meaning for 'query' or 'limit' beyond what their names imply. Unlike the covered 'response_version', the two main operational parameters are left undocumented in both the schema and the description, so the description does not compensate for the coverage 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 states a specific verb ('Search'), a precise resource ('external MCP servers registered in Siglume MCP Router'), and explicitly contrasts itself with siglume_search for broader discovery. This clearly differentiates it from its sibling and from the alternative search 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?

It gives an explicit scope limitation ('only external MCP servers registered in Siglume MCP Router') and names the alternative for broader discovery ('use siglume_search'). This tells an agent exactly when this tool is appropriate and when another tool should be selected.

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