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

Annotations already declare destructiveHint=true and non-read-only, so the safety profile is covered; the description adds real context beyond that: a history line is recorded, write permission in the project is required, unspecified fields are left untouched, and an existing term that the caller cannot open survives the replacement. That last detail is a non-obvious side effect no annotation could convey. It stops short of describing failure modes for a bad embedId, so not a 5.

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?

It is a single run-on sentence stitched together with em dashes and parentheticals, so key rules (empty sites, days 0, permission requirement) are buried mid-stream rather than separated out. Purpose is front-loaded, and nothing is strictly wasted, but the packing hurts scannability for an agent.

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 6-parameter destructive mutation with no output schema, the description covers what changes, what is preserved, who may call it, and the audit trail. Absent is any note on behavior when embedId is unknown or when set-only fields (title, terms, claims) are passed for a term or claim embed -- a realistic misuse case worth one sentence.

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 earns one step above it by explaining replacement semantics that the schema does not spell out: terms and claims are given as a list that replaces that part of the list, and entries the caller cannot open are retained. The 'empty sites / days 0' notes duplicate the schema descriptions rather than adding to them.

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 and resource -- changing a term's, claim's or set's link on other sites (i.e., the registry embed) -- and enumerates the mutable parts (sites, days, set name, terms, claims). It is distinguishable from create_*_embed and delete_registry_embed by implication, though no sibling is named explicitly. The dense phrasing slows parsing but the purpose itself is unambiguous.

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?

It gives the key precondition ("Only for somebody who may write in the project") and the partial-update rule ("Only what you pass changes"), which is genuinely useful invocation guidance. However, it never names alternatives -- delete_registry_embed, create_term_embed/create_claim_embed/create_embed_set, or update_wiki_embed -- nor says when to prefer them, so the routing decision 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.