check_session

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

With readOnlyHint=false and openWorldHint=true already declared, the description adds useful context: it explains that it invokes the server's own read-only tools repeatedly and attributes each menu change. It also discloses the guardrail that open-world tools are not touched unless open_world is set, though that narrows the openWorldHint annotation and the read-only phrasing is about downstream tools, not this tool's own side effects.

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, front-loaded with the purpose before the mechanics and the safety constraint. The middle sentence is dense and comma-spliced, packing the enumeration loop and the attribution rule together, but no clause is 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?

The description covers what the tool does, which downstream tools it will and will not call, and what it reports. For a seven-parameter tool with no output schema, it is nearly complete, though it says nothing about call failures, runtime, or the shape of the change report beyond 'each change with the call that caused it.'

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 100%, so the schema already documents cwd, env, url, command, headers, max_calls and open_world. The description adds only the meaning of open_world and the implicit constraint that a tool is only called if its arguments can be filled from the schema; it adds nothing for the connection parameters.

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 concrete verb and resource: it checks whether an MCP server's tool menu changes while an agent works, and it defines the mechanism (call read-only tools, re-list the menu, attribute each change to the call that caused it). It does not name or distinguish itself from the siblings snapshot_menu and diff_menus, so an agent must infer that this is the composite that runs those steps in a session.

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 eligibility rule for which downstream tools it will call (readOnlyHint only; no openWorldHint unless the open_world flag is set), which is real usage guidance. However, it never says when to choose this over snapshot_menu or diff_menus, so the choice among siblings is left implied.

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