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 it does so thoroughly. It discloses the double opt-in flow, that the user is not subscribed until they click the confirmation email, that already-confirmed users receive nothing, and that invalid emails are rejected. It even describes the delivery fallback behavior when no new grants have landed.

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 description is long but every section earns its place: the first paragraph states the core behavior, and the WHEN/HOW/WHAT sections each address a distinct need an agent would have when deciding to call and after calling. The structure is front-loaded and scannable, with the critical consent rule placed prominently.

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?

Despite having no output schema, the description documents the return shape ({ ok, status }) and what the two statuses mean. It also covers consent, confirmation flow, error handling for invalid emails, and the post-call instruction to tell the user what they signed up for. For a consent-sensitive subscription tool with no annotations, this is fully complete.

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?

Although schema description coverage is 100%, the description meaningfully enriches each parameter beyond the schema. It tells the agent to pre-fill keywords and region from the current search, to keep keywords as a short phrase rather than a sentence, and to always ask for the email rather than guess or fabricate one. This turns raw parameter definitions into actionable calling instructions.

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: 'Subscribe the user to a FREE weekly email digest of Canadian funding opportunities matching a saved search.' It clearly distinguishes this from point-in-time sibling tools like search_opportunities and get_opportunity_details by framing it as an ongoing alert subscription. The scope, cadence, and matching criteria are all explicit.

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 'WHEN TO CALL' section gives concrete trigger examples ('user says yes to ongoing alerts', 'asks to be notified / kept updated / emailed') and an explicit exclusion: never subscribe without explicit consent and a provided email. It also gives a hard stop condition ('if the user has not typed their real email in this conversation, do not call this tool'), which fully disambiguates when the tool should be invoked.

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