inspect_schema

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

With no annotations, the description must reveal behavioral traits. It does help by saying this is an 'inspect' (implying a read-only operation), and it notes pagination and the content ('tables + foreign keys view'). However, it does not explicitly state that it never modifies the schema, nor does it explain response size or how pagination is returned. A brief 'read-only' declaration would strengthen it, but it is at least passable for a non-destructive inspection tool.

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 three sentences, front-loads the core purpose first, and each additional clause provides necessary usage or behavior. There is no fluff, and it remains compact while covering purpose, mode, table filter, pagination, and the strategic advantage over list_* calls.

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?

Despite having 5 parameters, no output schema, and no annotations, the description gives a solid high-level of the tool's behavior and when to use it, saving the agent from parsing many list_* alternatives. It does not detail parameter semantics (especially model_id) or paginated response shape, which would make it fully complete, but for a read-only schema inspection tool the essential context is provided.

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 schema has 0% description coverage, so the textual description must compensate. It defines mode ('summary'|'detail'), mentions the optional single table, and indicates that the tool is paginated, which maps to the page/page_size parameters. It omits the significance of model_id entirely (a required parameter) and leaves summary/detail semantics to inference. Partial compensation, but not complete.

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 it inspects the whole schema at once, specifies the resource (schema) and type of output (tables + foreign keys view), and contrasts itself with the many list_* siblings. This leaves no ambiguity about what the tool does and how it differs from the alternative calls.

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?

It explicitly says 'use this instead of many list_* calls to save context', which names the alternative tools and gives a clear reason to use this tool. It also signals that a single table can be selected via the 'optional single table', but it does not spell out when NOT to use it (e.g., for fetching a single column or a specific relationship).

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