ass_tag_summary

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

With no annotations provided, the description carries the full behavioral burden and mostly succeeds: it declares 'Read-only; no snapshot', explains the meaning of missing_position as a typesetting smell, and clarifies that visible_chars counts only plain characters while all indices are 0-based. It omits any note on cost, scale limits, or behavior on large selections, so it falls short of exhaustive.

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?

It is front-loaded with the core purpose and the Args block is tight, but the long 'Returns' enumeration restates a structured fields that an output schema already exposes, so much of that prose does not earn its place. The sentence explaining missing_position is the part that genuinely adds value.

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 narrated, yet the description covers arguments, safety profile, and index conventions well enough for an agent to invoke it. The only substantive hole is the unspecified shape of the `selection` argument, which is the one thing an agent could still get wrong.

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 description coverage is 0%, so the description has to compensate and largely does: it maps index/text/doc_id to single-line inspection, explains that selection covers a set of lines with doc_id identifying the document, and states the 0-based convention. The one real gap is the type/format of `selection` itself (list of indices? ranges?), which remains unspecified in both schema and prose.

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 opening line states a specific verb-and-resource combination: it computes a per-line tag histogram AND performs a typesetting sanity check. That distinguishes it from pure-parse siblings like ass_parse_text or pure-stats tools like ass_stats. It does not explicitly name a sibling it supersedes or differs from, so it stops short of a 5.

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?

Usage is available only by inference from the Args block: index/text for one line, selection for a set, None for everything. There is no explicit statement of when to reach for this tool instead of ass_parse_text, ass_style_usage, or ass_get_line, which are the closest neighbours in the sibling list.

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