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

The description adds meaningful behavioral context beyond the annotations: it explicitly discloses that the tool does not mutate the current connection and that a new token is issued for subsequent /mcp requests. This is valuable because annotations only mark readOnlyHint=false without explaining the tool's actual side-effect 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?

Three sentences with zero waste: the first states the core purpose, the second discloses the non-mutation behavior and token usage, and the third routes operators to alternatives. Each sentence earns its place and the most critical scoping information is front-loaded.

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 one-parameter tool with an output schema present, the description covers purpose, behavioral effect, and post-call usage instructions. It does not address error cases such as invalid companyId or insufficient permissions, which is a minor gap given the output schema likely documents the return shape.

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%, and the schema already documents companyId with a helpful cross-reference to list_my_companies. The description adds no parameter-level detail beyond what the schema provides, 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?

The description uses a specific verb+resource pair ('Issue a new MCP access token scoped to another company/organisation') that precisely states the action and object. It distinguishes itself from any connection-mutating interpretation by explicitly clarifying that the current MCP connection is not changed, which is essential for a tool named 'switch_company'.

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 clear operational context: the client must use the returned token on later /mcp requests, telling the agent how to act after invoking the tool. It also provides an exclusion guideline ('Platform operators should prefer explicit-company admin tools when available'), though it stops short of naming specific sibling tools.

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