mcp_sandbox

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

With no annotations, the description carries full behavioral burden. It helpfully discloses that changes are deferred ('applies on next connect') and that reset restores defaults, but it omits whether 'set' merges with or replaces existing grants, whether changes are reversible, and any auth/confirmation requirements — a meaningful gap for a security-sensitive mutation tool.

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?

A single, front-loaded sentence covering scope, the three actions, and the deferred-application constraint. No filler or padding.

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 9-parameter, multi-action tool with full schema coverage and no output schema, the description covers purpose, actions, and timing. The one material omission is set/replace merge semantics for the grant fields, which matters for correct invocation.

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 every parameter, including enum meanings and example values. The description's mention of env/network/filesystem/subprocess categories adds framing but no semantics beyond what the schema provides, so baseline 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 (view/customize) and a specific resource (a server's sandbox capability manifest), and immediately names the capability domains (env/network/filesystem/subprocess). This is clearly distinguishable from siblings like mcp_connect or mcp_server_info.

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 explains all three actions and their intent, and adds the key usage condition that 'set' grants apply on next connect, which tells an agent when in the lifecycle to call it. It does not name sibling tools as alternatives or state prerequisites (e.g. server must be discovered/known).

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