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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior: the return format ('Returns Markdown') and a data-integrity guarantee ('Invents no costs: blank figures are left out'), which tells the agent it can safely omit optional parameters. Length/latency or how missing required context degrades output is not addressed.

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 front-loaded sentence that starts with the verb and resource, then enumerates output sections. The enumeration is long but each item corresponds to a real section of the deliverable, so it earns its space; the return-format and no-invented-costs clauses are packed efficiently at the end.

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?

With no output schema, the description correctly compensates by stating the return type (Markdown) and summarizing its sections, and the readOnly annotation removes the need to explain side effects. The gap is input-side: for a 15-parameter tool at 33% schema coverage, an agent has limited guidance on the optional numeric inputs needed to build the five-year cost table.

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 only 33% across 15 parameters, so the description must compensate and it only partly does: it clarifies that the cost table derives 'from the buyer's own figures' and that a 'not-to-exceed amount' goes into the motion. Many parameters (bus, need, signer, organization, listing_url, passengers, wheelchair_lift) receive no semantic elaboration, and the not_to_exceed-defaults-to-price behavior is left to the schema.

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?

Specific verb ('Write') plus a concrete artifact ('bus purchase proposal') with an enumerated table of contents: need, bus, van comparison, driver/license plan, five-year cost table, funding, inspection plan, draft motion. No sibling tool produces a document, so the distinction from check_cdl_requirement or compare_own_vs_outsource is unmistakable.

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?

The description names the target audience precisely (church, school, camp or senior living board), which implicitly tells the agent when this tool applies. It does not name alternatives or say when-not to use it — e.g., no pointer to check_vehicle_rules or get_used_bus_prices as prerequisite steps — so it falls short of a 5.

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