set_site_alert

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

Annotations indicate readOnlyHint=false and destructiveHint=false. The description adds context about the non-destructive nature (creating an email alert), restrictions on free tier (forced to bound email), and what triggers the alert (DCPI, capacity, facilities). It does not contradict annotations. However, it could mention if alerts can be modified or deleted, but overall transparent enough.

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 relatively long but well-structured: purpose first, then details, then constraints, then example. Every sentence adds value, though some phrases (e.g., 'FREE with a key') could be integrated. The front-loading is effective, and the 'Do NOT' section clarifies boundaries. Slightly verbose but earns its length.

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?

Given no output schema, the description still specifies the return format ({ok, alert_id, message}). It covers all necessary context: prerequisites (save_site, bind_email), tier limitations, parameter explanations, and exclusion of related tasks. It is complete for a tool with 4 parameters and no nested objects.

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 0%, so the description carries full burden. It defines each parameter with data types, default values, allowed values (trigger_type enums), and sources (saved_site_id from save_site/list_saved_sites). It also provides an example invocation. This fully compensates for the lack of schema descriptions.

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 clearly states the tool's purpose: 'Arm an email watch on a site you already saved'. It distinguishes from sibling tools by explicitly stating not to use for markets or saving new sites, and references specific alternatives (set_market_alert, save_site). This meets the criteria for specific verb+resource with sibling differentiation.

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 provides explicit when-to-use (watch a saved site) and when-not-to-use (whole market or new site). It outlines required prerequisite steps (call save_site first, bind_email if free tier) and suggests alternatives (set_market_alert, save_site). The usage loop is clearly described, making it easy for an agent to follow.

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