manage_scheduled_reports

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=false, which signals a mutating, externally-visible operation. The description adds nothing behavioral on top: it never mentions that cancel/pause are state-changing, that creates are non-idempotent (idempotentHint=false), or anything about delivery mechanics. The name's 'manage' hints at a multi-action lifecycle, but the description leaves it undisclosed.

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?

A single tightly written sentence with no filler, front-loaded with 'Use when'. It is efficient, though it spends its one sentence entirely on usage framing rather than distributing attention across purpose and operations.

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?

This is a 6-action lifecycle tool with 10 parameters, a required 'action' discriminator, and no output schema. The description does not explain any action, what each returns, or how schedule_id gates cancel/update/pause/resume. For a tool this complex, the usage-only sentence leaves major operational context 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 description coverage is 90%, so the schema itself documents email, query, brands, graphs, cadence, timezone, report_type, schedule_id, and slack_webhook in detail. The description contributes no additional parameter meaning, and notably never explains the required 'action' enum, which is the one gap the schema leaves. 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 description only frames the tool as usage scenarios ('establishing recurring intelligence tracking', 'setting up automated briefings') and never states what the tool actually does operationally. An agent learns that scheduling is involved but not that it supports create/list/cancel/update/pause/resume. Purpose is inferable from the name and title rather than from the description text.

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?

It gives clear, concrete when-to-use conditions: recurring tracking, automated briefings, and recurring category/brand shift monitoring. No when-not conditions or alternatives are named, but no sibling tool in the list competes for this scheduling job, so the omission is minor.

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