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

Annotations already establish readOnlyHint=true, idempotentHint=true, and destructiveHint=false, lowering the burden. The description adds genuinely new behavioral context: 'Empty is allowed' discloses that a valid result may be empty, and 'A bed is not presence' defines the semantic boundary of what 'present' means in this system. No contradiction with annotations — GET matches the read-only and non-destructive hints.

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, each earning its place: endpoint, scope, expected-empty caveat, and semantic boundary. The most identifying information (endpoint + filter) is front-loaded, and there is zero filler or repetition.

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 read-only list tool, the description covers the operational facts an agent needs: what it returns, that empty is valid, and what 'presence' excludes. Output schema exists, annotations cover the safety profile, and the schema fully documents all parameters. The only modest gap is no explicit relationship to the sibling peers tool, but nothing material is missing 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 description coverage is 100%, so the baseline is 3 even though the tool description mentions none of the four parameters. The description's 'present=1' refers to a fixed endpoint filter, not one of the schema params, so it adds no meaning beyond what the schema already provides for nonce, leave_token, controller_signature, and controller_public_key.

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 the resource and verb via the endpoint 'GET /api/peers?present=1' and clarifies scope with 'Only present peers.' The line 'A bed is not presence' distinguishes this tool from sibling present_bed/present_look, and the present=1 filter separates it from the unfiltered peers sibling. Slight deduction because the verb is implicit in the HTTP method rather than stated plainly, and the title is null.

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 usable context: 'Empty is allowed' tells the agent not to treat an empty result as an error, and 'A bed is not presence' implies this tool is the wrong choice for bed-occupancy checks. However, no alternative tool is named explicitly (e.g., 'use present_bed instead'), so the routing guidance is implied rather than stated.

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