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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuinely non-obvious behavior: omitted filters are preserved (merge semantics), the ID/name/email setting survive, account preferences are untouched, and an email-enabled search gets a fresh baseline. It stops short of saying what happens on an invalid ID or whether the change is reversible.

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?

Four short sentences, front-loaded with the core action, then the merge rule, then preserved state, then the email-baseline consequence. Every sentence adds a distinct fact; nothing is redundant with the title or schema.

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 mutating tool with a nested filter object, no output schema, and annotations that already flag destructiveness, the description covers the behaviors an agent most needs: partial update semantics, identity preservation, and the email consequence. Only error/validation behavior and how to obtain a valid saved_search_id are left unaddressed.

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?

Top-level schema description coverage is 0%, so the description carries the burden, and it delivers the single most important semantic: "Omitted filters stay unchanged," which is a merge-patch contract not stated anywhere in the schema. The nested filter properties are well documented in the schema itself. The gap is saved_search_id, which is undocumented in both places beyond its UUID format.

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?

"Change criteria on an existing saved search in place" gives a specific verb (change), resource (saved search), and scope qualifier (in place) that separates it from save_search (create) and set_filters (active filter state). The follow-on clause enumerating what is preserved further pins down the operation.

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 phrase "on an existing saved search" implies this is the edit path rather than the create path, and "omitted filters stay unchanged" tells the agent a partial payload is valid. But no sibling is named explicitly, so the agent must infer that save_search creates and delete_saved_search removes, and there is no statement of prerequisites such as needing a valid saved_search_id.

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