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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description supplies the missing context: the default path is a read, the write path requires admin scope, is estate-wide and audited, and the response then carries `saved`. It also discloses a domain rule ('In-process never runs while external runners are configured') and the meaning of holdReason. It does not say whether a declaration change is reversible or affects in-flight runs, keeping it off a 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?

It is front-loaded with the purpose and every clause carries information — the runner-count list, the state enum, the holdReason gloss and the admin/write path. The dense em-dash chaining makes it harder to scan than it needs to be, but there is no filler to cut.

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 correctly carries the return burden by naming the fields an agent will get back (mode, declaration, source, runner counts, lastSeenAt, state, holdReason, saved). The read/write split and admin gating are both stated. Error or remediation paths for a degraded/unconfigured state are not described, which keeps it at 4.

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% and the sole parameter's description already covers the admin scope, the three allowed values and 'omit to read only'. The description adds only the audit/`saved` consequence, which is a genuine but small increment over the schema, so the baseline 3 applies.

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 opening clause 'Where CI runs and why' plus the enumerated facets (mode, declaration and its source, runner counts, lastSeenAt, state, holdReason) makes the resource and scope concrete. It stops short of naming how it differs from siblings like merjax_ci_health, merjax_ci_queue_status or merjax_list_runners, even though it references the /admin/runners endpoint those tools likely wrap.

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?

It does give one clear conditional: omit `declare` to read only, and site admins may pass it to write. That is real when-to-use guidance for the two modes. However, there is no guidance on when to pick this over merjax_ci_health, merjax_ci_queue_status or merjax_list_runners, so sibling selection is left to inference.

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