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

Annotations give only the coarse safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false); the description adds the real behavioral detail: existing addresses gain a source rather than erroring, lastSeenAt/lastSource move, created returns false, existing names are never overwritten and nameKept signals it, and filled names are attributed to the team (nameSetBy). It also warns that titles, summaries and viewer text in results are untrusted author/reader content, which annotations cannot convey.

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 purpose is front-loaded in the first clause and each sentence carries concrete behavior, but the prose is clause-heavy and the 'for a person the workspace already knows and the product has not seen' sentence is dense and slightly cryptic. Efficient overall, marginally over-written.

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?

There is no output schema, so the description carries the full return-value burden and does so: created, replayed, nameKept and contact.name are all explained, including the duplicate and name-preservation outcomes. For a 3-parameter mutation tool with no output schema, nothing an agent needs is 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 coverage is already 100%, so the baseline is 3, but the description adds genuinely new semantics beyond the schema: the email is the identity, is required and is folded to lowercase, and a supplied name only fills a blank rather than overwriting. The interaction between the idempotencyKey and duplicate suppression is explained in the schema and reinforced in the description.

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?

States a specific verb+resource+key ('Adds somebody to the workspace's contacts by email address') and immediately distinguishes itself from a sibling by declaring that renaming is lnkdrp_update_contact's job. An agent can tell this apart from update_contact, get_contact and list_contacts without opening their schemas.

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?

Gives a clear usage scenario (contacts are added as people read a share link) and an explicit alternative plus the condition selecting it ('renaming a contact on purpose is lnkdrp_update_contact's job'). It also clarifies that re-adding an existing address is not an error, which is decision-relevant. It stops short of a full when-to-use/when-not framework, so a 4 rather than 5.

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