ghl_clientportal_list_templates

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

Annotations already declare readOnlyHint/idempotent/non-destructive, and the description adds a useful OAuth scope (clientportal-ai.readonly). But the leading 'side-effecting: opens/edits sandboxes and starts builds' preamble mischaracterizes a pure read/list endpoint and could make an agent hesitate, offsetting the added value.

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 relevant content is well-organized and informative, but roughly a quarter of the text is front-loaded with API-family boilerplate about sandbox editing and 409s that does not apply to listing templates, hurting front-loading.

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 usefully enumerates what each catalog entry contains and how the id feeds createProject, plus the endpoint and scope. The misleading preamble is the main deficiency for a read-only, parameterless tool.

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, so there is nothing to explain and the baseline is 4. The description instead details the returned entry fields, which is helpful but belongs to output/context rather than input semantics.

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 sentence 'List the app templates a project can be created from' states a specific verb and resource, and the entry-field enumeration (id, category, name, version, stackTemplate, previewUrl) plus the createProject linkage distinguish it from siblings such as ghl_clientportal_create_project. It stops short of 5 because that sentence is buried behind a boilerplate preamble that describes sandbox/open-build behavior irrelevant to a list.

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?

The description implies usage by saying to pass the chosen id as templateId on createProject, and contextualizes the catalog as powering the template picker. However, it never explicitly states when to call this versus alternatives or preconditions for calling.

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