ass_get_selection

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

With no annotations, the description carries the full burden and does disclose real behavior: out-of-range indices are silently dropped and indices are 0-based. It does not state whether a document must already be open or what happens on an empty selection, but the pruning rule is genuinely useful context.

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?

Front-loaded with the one-line purpose, then the return shape and the dropping rule. Tight and waste-free, though the embedded JSON-shaped return listing is slightly heavy prose.

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?

An output schema exists, so return values need not be spelled out, yet the description adds useful semantics (0-based indexing, out-of-range pruning) that an agent needs. The only real gap is the missing call-context guidance against sibling selection tools.

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. The index-base note (0-based) is about returned values rather than inputs, but it is the only semantic the schema could not convey.

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?

States a specific verb (read back) and resource (the session selection), immediately distinguishing it from write-side siblings like ass_select. The return payload is named concretely (doc_id, selection indices, count, lines), so an agent knows exactly what comes back.

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?

There is no explicit when-to-use guidance, no mention of the natural counterpart ass_select (which sets the selection being read), and no stated preconditions such as requiring an open/active document. Usage is only inferable from the tool name.

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