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

Annotations already declare readOnly/non-destructive/closed-world, so the safety profile is covered. The description adds real value by disclosing the searched fields (subject and headers only, not body) and the permission scoping, but omits case sensitivity, result ordering, default limit, and what a match returns.

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 with no filler; the searched fields and scope both appear before any caveats. Nothing to trim.

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 should say what a result looks like (full messages vs. snippets) and how limit defaults. It covers search scope and permissions but leaves return shape and empty-result behavior unstated for a 3-parameter tool.

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 67%: query and inboxId are documented in-schema, but limit has no description and no stated default despite a 1-50 range. The description adds nothing about parameters, so it functions at the baseline rather than compensating for the 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?

States a specific verb and resource ("literal substring search over subject and headers") plus the scope constraint ("granted inboxes"). An agent can see this is a search tool distinct from a plain list, but no sibling tool (list_messages, get_message) is named to sharpen the distinction.

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?

No guidance on when to prefer this over list_messages or get_message, and no mention of what to do when the substring doesn't hit the body. The only implicit cue is the "granted inboxes" scope in the schema's inboxId default.

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