session_select

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

The description discloses the silent failure mode (native value setter belonging to HTMLInputElement has no effect) and explains the tool exists to prevent it. It additionally spells out the matching order, the return object shape {selected, value, text}, and the failure behavior (lists available options). This goes well beyond the annotations (readOnlyHint false, idempotentHint true, etc.) and gives a complete picture of runtime behavior.

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 concise yet information-dense, with every sentence serving a purpose: stating the core action and selection methods, explaining a common pitfall, detailing the matching precedence, and specifying output and error behavior. It is front-loaded with the purpose and avoids any redundant phrasing.

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 dropdown-selection tool with moderate complexity, the description covers all aspects an agent needs: how to choose (methods), why not to use alternative methods, the order of resolution, the return value, and error handling. There is no output schema, but the description compensates by specifying the return shape. Combined with the thorough schema and annotations, nothing essential is missing.

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 coverage is 100%, so the baseline is 3. The description adds meaningful context by explaining that value is tried first, then exact text, then substring, then index, which clarifies the interplay between the value, text, and index parameters beyond their individual schema entries. It also notes that ref is used instead of selector, reinforcing the schema's wording. This adds moderate value above the schema, warranting a 4.

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 states the specific verb 'choose' and the resource 'option in a <select> dropdown', then elaborates on the three selection modes (value, visible text, index). It also contrasts itself with text-field filling, which is a sibling operation, making the purpose unambiguous and differentiated from session_fill.

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 explicitly warns that filling a select as a text field does nothing, thereby telling the agent when NOT to use session_fill and implicitly steering it to this tool for dropdowns. It also details the matching priority (value → exact text → substring → index), which helps the agent decide which parameter to supply based on the target option.

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