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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, which covers the core behavioral traits. The description adds context by noting 'including failed ones' and the diagnostic purpose, which are not explicit in the annotations but do not contradict them. No missing behavioral disclosures beyond what annotations provide.

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 concise, two sentences long, and front-loads the primary purpose. It clearly separates the action from the usage recommendation and references a sibling tool without extraneous details.

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?

The description gives a strong purpose and usage context but lacks detail on optional parameters (outcome, brand_id, limit, cursor) and does not explain pagination or response structure beyond listing a few fields. Since there is no output schema, more contextual guidance would be expected for full usage. It partially compensates by mentioning returned fields but remains incomplete.

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 low (only 1 of 6 parameters, 'query', has a description; the others have no description). The description only mentions that workspace_id is required (already in schema) and does not explain limit, outcome, brand_id, or cursor. It fails to compensate for the low schema coverage, providing minimal parameter guidance.

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 clearly states the tool lists recent OAuth connection attempts in a workspace, including failed ones, with platform, initiator, outcome, and error code. It explicitly distinguishes from the sibling aidelly_list_accounts by noting that this tool focuses on attempts (including failures) while the sibling lists successfully connected accounts.

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 gives explicit usage guidance: 'Use this to diagnose why a client could not connect an account; use aidelly_list_accounts for accounts that actually connected.' This directly states when to use this tool versus the alternative, leaving no ambiguity.

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