get_saved_positions

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

With no annotations at all, the description carries the full behavioral burden, and it does supply one genuinely useful fact: the required 'state' capability, which signals an auth/permission constraint. It says nothing about what a saved position contains, whether the result is a list, or what happens when none exist, so the disclosure is partial.

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?

Two short clauses, no filler, and the capability requirement is front-loaded so a caller learns the gate before anything else. The second clause is a fragment but still reads cleanly.

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 parameterless read tool this is close to sufficient, but with no annotations and no output schema, the description is the only source of behavioral detail and it omits the return shape (list vs object) and per-item fields. Minor gaps, but they are the only remaining source of truth.

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 the baseline is 4; there are no arguments whose meaning the description needs to disambiguate. Nothing in the description conflicts with the empty schema.

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 names the resource precisely (saved positions) and its source (the device profile), which is more informative than a bare restatement of the name. It does not, however, distinguish this from the sibling get_position, leaving the agent to infer that one returns a single/current position while this returns a stored collection.

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 only guidance is the precondition 'Requires capability "state"', which is a gate, not a usage rule. There is no statement of when to prefer this over get_position or get_state_snapshot, and no when-not guidance.

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