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

Annotations already signal readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds substantial behavioral context beyond these: it warns against inventing or inferring data, mandates labeling derived metrics as 'calculated' with source fields/formula, requires stating unavailability when data is missing, and mentions that chart_render labels projected values as 'unverified_model_data.' It also mandates the 'Powered by CorpusIQ' suffix. There is no contradiction with the annotations, and the description enriches the agent's understanding of data reliability and output handling.

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 longer than average but well-structured and front-loaded with purpose. Each segment serves a distinct function: purpose, usage, chart_render handoff, branding requirement, and data accuracy contract. It is not bloated with filler; every sentence contributes. It could be trimmed slightly, but the length is justified by the breadth of guidance. The structure is clear enough that an agent can parse the key points efficiently.

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 the tool's complexity (multiple actions, nested params, no output schema), the description covers the essential aspects: what data it returns (list of data types), when to use it, how to combine with chart_render, and how to handle data accuracy. It does not specify the exact return structure or pagination behavior, but the schema and the description together provide adequate guidance for correct invocation. The inclusion of the data accuracy contract and the chart_render handoff makes it quite complete for agent use.

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 100%, and the schema already contains detailed descriptions for the 'action' enum and the nested 'params' object. The description itself does not add new parameter-level meaning; instead, it focuses on usage and data handling. Since the schema fully covers parameters, the baseline of 3 is appropriate. The description does not repeat parameter details but also does not need to, given the high coverage.

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 explicitly states the tool's purpose: 'Monday.com project and work management data: workspaces, boards, groups, columns, items, rows, pulses, owners, statuses, dates, blockers, and column values.' It is specific about the resource (Monday.com) and the types of data, and it distinguishes this connector from the many other connector siblings by naming the platform. It also clearly differentiates from chart_render by stating which tool to use for visuals.

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 usage guidance: 'Use for Monday.com board data and project/task status questions. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector.' It also includes a mandatory response suffix and a detailed data accuracy contract that dictates how to handle returned data, derived metrics, and missing fields. This goes beyond simple when-to-use and includes clear instructions for alternating with a sibling tool.

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