tenki_update_ssh_keys

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

Annotations already carry the core safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true), so the description's burden is reduced. It adds the prerequisite that the sandbox must be running and explains the effect (enabling SSH access). The important replacement behavior ('Replaces the current set') is disclosed only in the schema, not the description, but it is available to the agent. No contradiction with annotations.

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 efficient sentence that front-loads the verb and object, with the purpose clause earning its place by explaining why an agent would invoke it. No filler, no repetition of schema content, no wasted words.

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 2-parameter tool with full schema coverage, no output schema, and no nested objects, the description covers action, target, and effect — which is nearly complete. The remaining gaps are minor: no routing guidance against tenki_issue_ssh_cert and the replace-semantics appear only in the schema rather than the description an agent reads first.

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%: session_id is explained with its provenance (from tenki_create_sandbox or tenki_list_sandboxes) and public_keys includes formats and the replace-semantics. The description adds only the overall purpose ('enabling direct SSH access'), which adds marginal meaning beyond the schema. Baseline 3 applies because the schema does the heavy lifting.

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?

Uses a specific verb ('Set') with a specific resource ('SSH authorized public keys on a running sandbox') and states the resulting effect (direct SSH access). This is clearly distinguishable from sibling tools like tenki_issue_ssh_cert (certificate issuance) and tenki_exec (command execution) without needing to open their schemas.

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 usage context is implied: call this when you want to enable SSH access to a sandbox via public keys, and the 'running sandbox' phrasing hints the sandbox must be active. However, there is no explicit when/when-not guidance and no mention of the closely related alternative tenki_issue_ssh_cert, so an agent gets no help choosing between key-based and cert-based SSH auth.

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