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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add context — and it does, by describing the return shape (latest available year, all chapters, publication dates) and the default behavior when no year is supplied. The provenance note (library source, CPA verification date) is an unusual but genuinely useful trust signal for a tax-domain tool.

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 core purpose, return contents, and follow-up tool are front-loaded and each sentence earns its place. The trailing provenance sentence is long and the bilingual restatement of the title in Hebrew adds no new information, which costs a point.

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 zero-required-parameter, single-parameter read tool with full schema coverage and no output schema, the description covers purpose, scope, return contents, filtering, and the natural next call. Minor gaps remain around edge cases such as a tax_year with no published guides, but nothing essential to invoking it correctly 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% for the single optional parameter, so the baseline is 3. The description adds only a light example ('e.g., 2025, 2026') and restates the default-to-latest behavior that the schema already declares, so it does not meaningfully deepen parameter meaning.

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 opens with a specific verb and resource ('List MISIM.AI guide chapters (kind=guide)') and immediately scopes it as a discovery tool, which cleanly separates it from siblings like misim_search_library, misim_list_laws, and misim_get_document. It also states what the result set contains (latest tax year plus all chapters in that year with publication dates).

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?

It gives a concrete usage context ('surface guides in annual-return and form-1301 workflows') and explicitly names the follow-up call, misim_get_document, to read a full chapter. It stops short of stating when to prefer this over misim_search_library or misim_list_laws, so an agent must infer the boundary between browsing chapters and searching content.

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