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

Annotations already declare destructiveHint=true, but the description adds the details an agent actually needs: deletion is visible to everyone in the conversation, is irreversible, is time-boxed to 60 minutes, and consumes a 100/day allowance. Rate limit and irreversibility are not encoded anywhere in the annotations or schema.

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?

Four short sentences, front-loaded with the action and scope, then the hard constraints in descending order of importance. No 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?

For a destructive two-parameter tool with strong annotations and no output schema, the description covers scope, irreversibility, time window and quota. Minor gap: it does not say what happens if the 60-minute window has lapsed (error vs. silent no-op).

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 both messageId and connectionId are already documented in the schema. The description adds only the implicit constraint that messageId must reference a message the caller sent; it clarifies nothing about connectionId or ID sourcing beyond the schema.

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 ('Delete ONE message you sent on LinkedIn'), plus scope qualifiers (one message, sent by you, for everyone in the conversation) that separate it from delete_chat and edit_message in the sibling list.

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?

Gives clear gating conditions — only messages you sent, only within 60 minutes — which effectively define when the call can succeed. It does not explicitly name alternatives (e.g. edit_message or delete_chat), so it stops short of full when-not routing.

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