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

Annotations indicate readOnlyHint=false and destructiveHint=false, which suggests this is a mutation but not destructive (maybe it's creation, which is neither read-only nor destructive). The description says 'Add' and 'Marks... on creation', so it's clear it's a write operation. It doesn't disclose anything about side effects like whether duplicate domains are rejected or whether it updates existing entries. Since annotations don't cover behavioral nuances, the description carries more burden, but it does state the creation and marking of importance. It doesn't describe what happens if the domain already exists, so a bit of a gap. Not a contradiction.

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 two sentences, concise and to the point. It includes an example for the domain which is helpful. It's front-loaded with the primary action. No fluff. Slightly better than minimal.

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 has 3 required parameters, all covered by name in the description, and no output schema, the description is relatively complete. It tells you what it does and the importance setting. But it doesn't mention what the response is (like success message or created object). It doesn't mention error conditions. For a simple creation tool, this might be enough, but there's room for more, like whether it returns the created competitor or just a status. However, many tools don't describe responses. I'd give 3.

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 0%, so the description must compensate. The description mentions 'project by domain' and 'important or ignored', which maps to projectId, domain, and importance parameters. It gives an example domain format in the text, which helps. The importance parameter has an enum in schema, so values are known. But it doesn't explain what each parameter precisely means (e.g., projectId is a UUID, domain format). The description adds some semantic meaning beyond the schema (like the purpose of importance), but not much beyond that. So I'd say 3 is appropriate.

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 states a specific verb ('Add') and resource ('competitor to a project by domain'), and includes an example domain. It also adds an elaboration on marking importance, which is distinct from the sibling 'set_competitor_importance'. However, it doesn't explicitly name a sibling or differentiate beyond that, so it doesn't fully distinguish from 'list_competitors' or 'set_competitor_importance', but it's clear enough.

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 implies usage: 'Add a competitor to a project by domain' and the importance flag. It doesn't explicitly state when to use this vs 'set_competitor_importance' or when not to use it. No alternatives or exclusions are mentioned. There's no mention of prerequisites (e.g., project must exist, domain must be valid). So it's adequate but lacks explicit guidance.

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