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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered without the description. What the description adds is lifecycle context: it is deprecated and will be removed after 2027-01-07, which is genuinely useful behavioral information not present in annotations. It adds nothing about result shape or filtering behavior, deferring entirely to the sibling.

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?

A single sentence with three tightly packed facts (identity, sunset date, equivalence) and zero waste. The most important signal — that this is the old name — is front-loaded.

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 deprecated alias the description supplies exactly the metadata needed to decide relevance: what it aliases, that behavior is identical, and when it disappears. However, with 12 undocumented parameters and no output schema, an agent that actually invokes it receives no parameter guidance and no indication of what a result looks like.

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?

There are 12 parameters at 0% schema description coverage, so the description carries the full burden of explaining them — and it explains none, offering only "same arguments and results: see `search_memories`." Delegation is defensible for an alias, but an agent calling this tool still gets no meaning for kind, team vs teams, detail, topics, include_expired, include_superseded, or max_chars without opening another tool's definition.

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 never states a verb+resource directly, but by declaring itself the "Old name for `search_memories`" with "Same arguments and results" it fully identifies what the tool does via the canonical sibling. An agent scanning the tool list can immediately classify it as the deprecated alias of search_memories rather than a distinct capability.

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 names the alternative (`search_memories`) and supplies the sunset date 2027-01-07, which gives the agent a clear signal that this is a compatibility shim and the canonical tool is preferred. It stops short of an explicit "use search_memories instead" instruction, so the preference is strongly implied rather than stated.

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