manage_bar_link

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

Annotations already carry destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the low-level safety profile is covered. The description adds genuine value beyond that: explicit failure conditions per action, the requirement to fetch IDs from get_bar_links, and the API limitation that update is unsupported. It aligns with, and does not contradict, 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?

The description is compact and front-loaded with the core purpose, then organized into labeled blocks (USE WHEN, Actions, FAILS WHEN, Note). Each sentence earns its place, though the Actions line partially restates what the input schema already enumerates. No redundancy or padding beyond that.

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 5-parameter mutation tool with no output schema, the description covers purpose, when to use, failure modes, where to source IDs, and the update workaround. The only gap is a statement of expected return/success behavior, which is minor given the annotations already flag this tool as destructive and non-idempotent.

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. The description adds an action-to-parameter contract that the schema lacks: create requires url, delete requires link_id. This conditional relationship between the action enum and other parameters meaningfully exceeds the flat per-field schema descriptions.

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 sentence states a specific action pair and resource: 'Create or delete external link on a bar.' The USE WHEN examples ('Link Jira ticket', 'Add design doc', 'Remove link') ground it in concrete user intents. It is clearly distinguished from siblings like get_bar_links (read-only) and manage_bar_connection (connections, not links).

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?

Provides an explicit USE WHEN block with example intents, and direct FAILS WHEN conditions for each action. It names the alternative tool (get_bar_links) for sourcing link_id and gives an explicit exclusion: update is not available via API, so delete-and-recreate is the prescribed path. Nothing is left to inference.

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