Per-connection health: status, token expiry, scopes and sync freshness

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered elsewhere. Beyond that, the description adds only the endpoint path (GET /v1/connections/health); it says nothing about what happens for expired tokens, whether unhealthy connections cause errors or per-item results, or the shape of the response. Since there is no output schema, that gap is on the description.

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?

One compact clause with zero filler, and the resource is front-loaded. It is a fragment rather than a sentence, and the parenthetical endpoint duplicates nothing but adds little for an agent that cannot make raw HTTP calls.

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 zero-parameter read tool with safety covered by annotations, this is close to adequate — it says which fields come back. But with no output schema, an agent still does not know whether results are per-connection objects or aggregated, nor whether expiry/scopes are flagged as problems.

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?

The tool takes zero parameters, which is the baseline-4 case: there is nothing for the description to disambiguate. The description correctly implies a workspace-wide sweep with no filtering arguments.

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 names the resource (per-connection health) and enumerates the four data points returned: status, token expiry, scopes, sync freshness. However, it is verb-less and essentially restates the title plus an HTTP route, so the distinction from siblings like connections_list or auth_me relies on the reader inferring 'health' means diagnostics rather than listing.

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?

There is no guidance on when to call this versus connections_list (which would show connections exist) or ops_health (service-level health). No preconditions, no mention of which connections are covered, and no exclusions. The agent must guess the diagnostic intent from the name alone.

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