ghl_clientportal_get_project_change_schema

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

Annotations already declare readOnlyHint/idempotentHint true and destructive false. The description adds genuinely useful context beyond them - the schema is static per server release, requires the Version: v3 header, and needs the clientportal-ai.readonly scope - but the leading side-effect warning and 409 note belong to other tools and could make an agent misread this as a mutating call.

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 description opens with roughly two sentences of unrelated API-wide warnings (sandbox edits, checkpointing, 409 ownership) that have nothing to do with fetching a schema, then buries the actual answer in the middle. The genuinely relevant content - static per release, one example per kind, endpoint, auth scope - is compressed into a couple of lines.

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 two-parameter read with full schema coverage and no output schema, the description covers what is returned, that results are static per server release, the exact endpoint and version header, and the required OAuth scope. Only the explicit ordering relative to `plan_project_change` is missing.

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%: both `projectId` (prj_ pattern) and `kind` (kebab/snake pattern, absent returns all kinds) are documented in the schema. The description adds no additional syntax or filtering semantics, so the schema carries the load and 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 core sentences state precisely what is returned: a JSON Schema (draft 2020-12 input shape) plus one valid example per change kind accepted by `POST /changes/plan`, tied to the concrete GET route. That is a specific verb+resource and distinguishes it from plan/apply siblings. However, the opening side-effecting/sandbox-sequencing sentence describes a different workflow and muddies the read-only nature of this call.

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: an agent can infer it should fetch this before composing a `change` for the plan endpoint, but the description never says so explicitly and names no alternative tool. The sandbox-editing and 409 guidance points at sibling tools (sandbox edit, checkpoint) rather than this one.

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