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

Annotations already declare read-only, idempotent and closed-world behavior, yet the description goes well beyond them: it discloses exactly what is returned, that each price carries a numeric value, currency and per-unit basis, that a response returns one price and names any superseded estimate, the semantics of the estimators block, and detailed failure semantics. It even adds the important caveat that estimates are neither supplier quotes nor live availability.

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 front-loaded correctly — resource, then payload, then edge cases — but it is delivered as three very long, clause-packed sentences with no formatting, making the estimator and not-found rules hard to scan. Every sentence carries real information, so this is a structure problem rather than padding.

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 and a single trivial input, the description carries the full burden of describing the return shape, and it does so thoroughly: payload contents, price representation, estimate provenance, the estimators block, and the not-found response. An agent can interpret the response without any additional documentation.

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 coverage is 100% and there is a single parameter whose description ('Unique slug identifying a published Aisle venue') is already complete. The description restates 'by its slug' and adds only the behavioral consequence of a non-published slug, which is useful but not parameter-syntax detail. Baseline 3 applies when the schema does the heavy lifting.

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 first clause states a specific verb and resource ('Returns a published wedding venue by its slug') and immediately enumerates the payload (photos, highlights, travel information, planning estimates, sourced facts with provenance). This is clearly distinguishable from search_venues (a lookup) and get_vendor_details (a different resource) without opening any schema.

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 only implied: the tool takes a slug, so the agent infers it is the follow-up to search_venues or list_venue_countries, but no sibling is ever named and no 'use this when' condition is stated. The not-found handling (never listed vs. taken down, plus suggested alternatives) partially compensates by telling the agent what to do when the lookup fails.

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