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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), so the description's job is to add context — and it does: it identifies the source series (Freddie Mac PMMS), the fact that these are weekly averages rather than daily quotes, the exact coverage window (1971-04-02 to today), and which rate products are included. It does not state how a mid-week date resolves to a weekly reading, which is the one behavioral detail still missing.

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?

A single sentence that front-loads the resource and provenance, then the coverage window. The parenthetical about 5/1 ARM and points is the only compression, and it carries real information rather than filler.

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 one-parameter read tool with full annotation coverage and no output schema, the description covers source, products, and valid date range — enough to call it correctly. The remaining gap is edge-case behavior (dates outside the range, non-publication days) and any hint about the return shape, though the latter is a minor concern given the tool's simplicity.

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?

With one parameter at 100% schema coverage, the baseline is 3, and the description earns a bump by supplying the valid domain (1971-04-02 to today) that the schema's pattern alone does not constrain. The YYYY-MM-DD format itself is already in the schema and is not duplicated.

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?

Names a specific resource (Freddie Mac PMMS 30-year and 15-year fixed rates, plus 5/1 ARM and points), a specific scope ('in force on a date'), and the data provenance. It stops short of naming the sibling tools (get_mortgage_rates_today, get_mortgage_rate_history), so the differentiation is only implied by the singular 'on a date' phrasing.

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 implied rather than stated: a single required date plus 'in force on a date' signals point-in-time lookup, and the sibling names make the today/history alternatives guessable. There is no explicit 'use this instead of X when Y' routing, and no note about what happens for a non-publication day or a date before 1971-04-02.

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