change_crm_chart

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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description goes beyond them by disclosing the solution/publication constraint for system charts and the ETag-based concurrency check for update/delete, which explains failure modes an agent would otherwise hit blind. It does not say what a preview returns or whether a failed concurrency check can be retried.

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?

Four short sentences, front-loaded with the action scope and followed by prerequisites in descending order of importance. No filler, though the ETag and expected_hash statements overlap enough that they could be merged.

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 destructive 12-parameter mutation with no output schema, the description covers the hardest prerequisites (publication, concurrency, hash-gated execution) but leaves the payload parameters and the preview return value unexplained. An agent still cannot construct data_xml or presentation_xml from this definition alone.

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 only 8%, so the description must carry the load; it adds real meaning for expected_hash (the ETag/concurrency token) and implies the system-scope requirement tied to solution_unique_name. However, it says nothing about data_xml, presentation_xml, entity_logical_name, dry_run, name, or id, leaving most of the 12 parameters unexplained in both places.

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 set (preview/create/update/delete) and specific resource (system or personal charts), which cleanly separates it from the read-side siblings list_crm_charts and get_crm_chart. It does not name those siblings explicitly, so the routing is implied by the verb rather than stated.

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?

'Preview then ...' establishes the intended dry-run-first workflow, and the description gives concrete preconditions: system scope needs an unmanaged solution plus table publication, update/delete need optimistic concurrency with a specific ETag, and execution needs expected_hash. What is missing is explicit guidance on when to skip the preview or where to obtain an id/ETag before calling.

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