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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds real behavioral context beyond that: the exact thresholds that produce SIZE_UP (avg CPU or memory ≥90%) versus SIZE_DOWN (both averages ≤30%, peaks ≤70%), plus the default 30-day lookback and the fields returned. Pagination/rate-limit behavior is left unmentioned, which keeps it below 5.

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?

The core purpose, thresholds, and default window are packed into one front-loaded sentence with no filler, so scanning yields the essentials immediately. The trailing internal API path ("Depot: GithubActionsService/ListGithubActionsRecommendations.") is decorative and doesn't help tool selection.

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 partly compensates by describing the returned fields (current vs suggested size, per-minute price). All 9 parameters are documented in the schema, and readOnlyHint covers safety, so the omission of pagination details and per-filter semantics is the main remaining gap.

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. The description adds meaning the schema does not: the 30-day default window gives an agent a concrete interpretation of the otherwise optional start_at/end_at parameters, removing the need to guess the temporal scope when filters are omitted.

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 ("List Depot's runner-size recommendations") and names the governing data source (job CPU and memory metrics), so an agent can distinguish it from adjacent listing tools such as depot_gha_list_jobs or depot_gha_get_analytics. The recommendation vocabulary (SIZE_UP/SIZE_DOWN) further pins down the resource.

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?

Usage is only implied: the description explains what triggers each recommendation type and that the window defaults to 30 days, which tells an agent when the output is relevant. But it never states explicit when-to-use or when-not-to-use conditions, nor names an alternative tool for raw metrics versus recommendations.

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