Call a backend tool

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

Annotations already declare destructive, non-readonly, non-idempotent, open-world execution, so the safety profile is covered; the description adds that side effects belong to the backend tool and that results are returned as text with a spill path for large payloads. It stops short of stating permission/confirmation requirements or what a spill looks like, keeping it below a 5.

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?

Roughly four short sentences with zero filler; the 'THIS IS THE STEP THAT ANSWERS THE USER' clause is front-loaded to anchor the tool's role. Every sentence carries a routing or return-behavior fact.

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 correctly covers the return shape (text, spill for large results), and annotations carry the risk profile for a destructive operation. The remaining gap is procedural: nothing tells the agent to call describe_tool to learn the backend tool's argument shape before invoking.

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?

Only `args` is described in the schema (33% coverage); the description supplies the missing meaning for server/tool as 'catalogue names', which is genuine added value. However, it never explains how `args` should be shaped relative to the backend tool's own schema or that describe_tool should be consulted first, leaving the most failure-prone parameter underspecified.

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 ('Invoke a tool on a connected server') and explicitly contrasts with the sibling list_capabilities ('only finds the name'). An agent can distinguish this as the execution step from the discovery steps without opening any 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?

Names the alternative (list_capabilities) and the condition that selects it, and adds a second routing rule for oversized results ('big ones via retrieve_spill'). Two sibling tools are positioned explicitly rather than left to inference.

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