List ADRs

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

With no annotations, the description carries the full behavioral burden and does well: it discloses pagination semantics (default 25, capped at 100) and the non-obvious clamping behavior ('out-of-range values are clamped, not errored'). It omits ordering guarantees and any permission/base-directory failure behavior, keeping it below 5.

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?

Dense but front-loaded — the return fields and scope come first, then the 'ref' caveat, then paging. Every clause carries information, though the em-dash aside about 'ref' makes the opening sentence long and slightly harder to parse.

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 no explanation, and both parameters are fully covered. The remaining gap is minor: no statement of ordering or what happens when the base directory is unset/unreadable.

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 0%, so the description must compensate, and it does: offset/max_results are explained as paging controls, with a stated default page size and a hard cap. This is meaning beyond the bare integer schema types.

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 (list) and resource (ADRs) plus exactly what is returned: ids, titles, statuses, refs. It also scopes the source (SPECMGR_ADR_DIR) and distinguishes itself from the sibling get_adr by saying it is for context 'before addressing one by id'.

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?

Gives clear context for use ('for context before addressing one by id') and routes the ambiguous 'ref' case to get_adr explicitly. It does not, however, say when to choose this over other list_* siblings or note any prerequisite state.

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