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

Annotations only declare readOnlyHint=false, so the description must disclose behavioral traits. It does state that every row becomes or matches a contact and that contacts get tagged, which is a clear side effect. However, it does not mention whether the operation is idempotent, what happens to existing contacts, or any error scenarios. For a mutation tool, this is a moderate gap.

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 is compact and front-loaded with the core purpose, followed by procedural steps. Each sentence adds value, and there is no redundant information. The flow from outcome to file-location to publication subdomain is logical and easy to parse.

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 an import tool with no output schema, the description covers the main inputs, the expected outcome (tagging and matching), and a required clarification (publication subdomain). It does not explain what happens on failure or if a result is returned, but these are less critical for an agent deciding whether to invoke the tool. The description is adequate for correct invocation.

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 100%, so all parameters are already documented. The description adds slight clarification (e.g., publication subdomain format and asking if unknown) but mostly reiterates the schema. It does add context on how to obtain object_id via search_graph_objects, but that is already in the schema description. Thus, it barely exceeds the baseline for high coverage.

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 description clearly states a specific action ('import') on a specific resource ('Substack subscriber export') and explains the outcome (rows become or match contacts tagged 'Substack subscriber' with plan and status). It distinguishes itself from read-only Substack tools like get_substack_subscribers and generic imports like import_contacts_from_file by focusing on the export CSV and the tagging behavior.

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 gives explicit guidance on how to prepare the input: locate the file via search_graph_objects and pass object_id or filename. It also instructs to ask for the publication subdomain if unknown. It does not explicitly contrast with sibling tools, but the specific file and publication requirements make the use case clear enough for an agent to select it appropriately.

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