init_session

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

No annotations are provided, so the description carries the full burden. It discloses that the tool scans, filters, and caches data, which is a meaningful behavioral overview. However, it does not explain side effects of calling it more than once (despite saying 'must be called once'), nor does it mention any permission requirements or potential errors. This is adequate but incomplete.

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 two sentences long, front-loaded with the action ('Scan all accessible models...') and ends with a clear prerequisite. Every sentence contributes meaning, and there is no redundancy or filler.

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?

The tool has no output schema, so the description should explain return behavior, but for an init function the return is likely secondary. The description covers the core actions (scan, filter, cache) and the usage context (must be called first). It lacks detail about what 'cached' means for subsequent tools or failure modes, but given the tool's simplicity, it is reasonably complete.

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 has zero parameters and the schema is an empty object, so schema description coverage is effectively 100%. With 0 params, the baseline is 4, and the description adds no parameter-level detail because none is needed. This is appropriate.

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 the tool's function: 'Scan all accessible models, admit only those with AI Model Metadata and AI Module Metadata sentinel modules, cache their modules and tagged line items.' It uses specific verbs (scan, admit, cache) and specifies the resource (models, modules, line items). It also distinguishes itself from sibling data-reading tools by noting it must be called 'once before any data-reading tool.'

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 provides explicit timing: 'Must be called once before any data-reading tool.' This clearly indicates when to use the tool relative to read tools like read_module_summary and read_module_detail. However, it does not mention when not to use it or provide alternatives, so it lacks the full when/when-not/alternatives guidance.

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