Zovo Meeting Planner

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

Annotations already declare readOnly/idempotent/closed-world, and the description still adds substantial context: it discloses the return contents (UTC offset, abbreviation, +/-1 day shift, hour difference, 7-day DST warning) and states it explains skipped or repeated local times caused by DST. That is real behavioral detail beyond the structured fields.

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?

One dense but well-ordered paragraph: trigger first, then inputs/return shape mid-way, then exclusions last. Every sentence carries information; no filler.

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 4-parameter conversion tool with annotations and an output schema, the description covers trigger, input formats, output shape, DST edge cases, and out-of-scope uses. Nothing an agent needs in order to call it correctly is missing.

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%, so baseline is 3. The description nonetheless reinforces accepted source formats (city, IANA zone, US state, country, UTC offset, abbreviation), the max 20 targets, and the ambiguity handling for IST/CST/AST/BST, adding usable phrasing that eases correct invocation.

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?

States a specific verb (convert) and resource (time between time zones/cities), and gives concrete example phrasings such as 'convert 3pm PST to IST'. It also names the sibling it is not (find_meeting_time), so an agent can distinguish them without opening either 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?

Opens with an explicit 'use this when' trigger, then lists explicit exclusions: does not plan meetings (routing to find_meeting_time), does not look up flight times, does not convert units. When-to-use and when-not-to-use are both covered with the alternative named.

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

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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes far beyond them: it discloses the ranking cost function, that night hours (22:00-07:00) and days off weigh more, the 10-slot cap with default 5, and the fallback that returns the closest time within 7 days after the range when no in-hours slot exists. It also states the exact contents of each slot (local times, status, .ics link, flexible window, equivalent dates), which the agent cannot infer from the annotations.

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?

Front-loaded with the usage trigger, then mechanics, then outputs, then exclusions in a deliberate order that matches how an agent would evaluate a call. The long sentence about slot contents is dense but every clause carries distinct information (ranking, slot fields, fallback).

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?

Covers the full decision surface for a 11-parameter tool with a nested participant object: when to use it, the search-range constraints, the ranking semantics that explain why slots come back in a given order, the single-slot escape hatch, and what it explicitly cannot do. Nothing needed to call it correctly is missing.

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%, so the baseline is 3, and the description earns an increment by explaining relationships the schema states only in isolation: participants are 2-8 with the first defining the reference date range, dates span up to 14 days, and selected_start_utc switches the call into a single-slot .ics lookup mode. It stops short of adding syntax detail for work_start/work_end or step_minutes beyond what the schema already documents.

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?

States a specific verb and resource ('find a meeting time across time zones') and immediately grounds it in a concrete example ('find a 1-hour slot for New York, London and Bangalore on 2026-11-10'). It is unmistakably a planning tool, not a conversion tool, so an agent can distinguish it from the convert_time sibling without opening the 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?

Opens with an explicit trigger ('Use this when the user wants to plan a meeting across time zones... working-hour overlap for a distributed team') and closes with clear exclusions ('does not read calendars, check availability, issue invitations'). The only gap is that it never names convert_time as the alternative for plain time conversion, leaving that routing to inference.

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