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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is partly covered; the description adds real value beyond that with partial-update semantics ("Only the fields you pass change"), the fact that running deployments keep old settings, the refusal list, and the encrypted-placeholder rejection. The notable gap is that ports/env "REPLACE the version's whole list" is a data-losing behavior that sits uneasily with destructiveHint=false, and the description does not reconcile that or state that nothing is sent on refusal beyond the placeholder case.

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?

Purpose is front-loaded and nearly every clause carries operational information, but it is one dense paragraph of roughly 200 words with stacked parentheticals, which makes the replacement and coupling rules hard to scan. Bullet or sentence separation for the ports/env and cpu/memory rules would improve it without adding length.

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 19-parameter mutation tool with no output schema, the description covers everything an agent needs to call it safely: partial-update behavior, list-replacement hazards, the read-before-write sibling, parameter coupling, refusal conditions, and the effect on already-running deployments. The remaining schema-documented fields are self-explanatory at 95% coverage.

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 95%, so the baseline is 3; the description earns above that by documenting cross-parameter rules the schema cannot express, notably that cpu_units and memory_mb must change together, that omitting the registry login preserves it, and that ports/env must be fully re-sent. It does not add meaning for the remaining parameters (verify_image, endpoint_storage, dry_run details) beyond what the schema already says.

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?

"Change settings on an existing version instead of creating a new one" gives a specific verb and resource and immediately contrasts the tool with edgegap_create_app_version. The follow-on list of mutable fields (image tag, is_active, max_duration, registry login, force_cache, restart policy, grace period) lets an agent confirm scope without opening the schema.

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?

Explicitly routes the agent away from creating a new version and names the alternative when that is required (registry_profile "Edgegap" cannot be added, so create a new version). It also directs the agent to edgegap_get_app_version to read current ports/env before a replacing update, and to edgegap_deploy for one-off resource overrides.

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