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

With no annotations, the description does carry real behavioral disclosure: it is BETA, the live source is not wired, it currently returns UNKNOWN, UNKNOWN is never charged, and data is as of 2026-10-26. That is genuinely useful context an agent would otherwise lack. However it omits what a non-UNKNOWN response looks like, what permissions/auth are needed, and what 'ESA limits' means semantically.

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?

It is a single sentence, but nearly all of it is verification/marketing metrics (100% golden accuracy 78/78, 100% uptime 24h) that crowd out the actual purpose. The name is redundantly repeated at the front instead of a functional statement being front-loaded.

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 3-parameter, unannotated, no-output-schema tool with 0% parameter coverage, the description should explain what is being looked up and what comes back. It only states the current degenerate return (UNKNOWN) and data freshness, leaving the agent unable to interpret a successful response or the month parameter.

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% across 3 parameters (lat, lon, month) and the description says nothing about them. It never explains that lat/lon is the query point, what coordinate convention applies, or what month scoping (1-12) does. All parameter meaning must be guessed from the schema's types and bounds alone.

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 never says what the tool actually returns — it only restates the name ('get_esa_limits') and then lists beta status and accuracy metrics. 'ESA limits' is never expanded (Endangered Species Act species/critical-habitat limits?) and no verb+resource statement of function is given. An agent cannot tell from this text what the tool computes for a lat/lon.

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?

There is no when-to-use guidance and no routing against the many overlapping siblings (check_use_allowed, check_license, solar_siting_check, spray_check, check_airspace). The only implied usage cue is that it is free and returns UNKNOWN without charge, which hints 'safe to call' but not when it is the right tool.

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