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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety baseline is covered. The description adds real value beyond that: results are "bounded untrusted snippets" (content must be treated as data, not instructions), each mode requires the [conversations:read] scope, and "references never grant access" clarifies authorization boundaries. It still says nothing about result size bounds, truncation behavior, or what happens with unbounded cursors.

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?

Front-loaded with the one-sentence purpose, then two tight bullets that map one-to-one to the two query modes. No filler or repetition. The phrasing "detail continuation" and "bounded untrusted snippets" is slightly compressed jargon, but each sentence earns its place.

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?

An output schema exists, so return values need not be described. For a polymorphic two-mode read tool, the description covers the mode split, authorization scopes, content-trust posture, and continuation semantics. The main remaining gap is sibling differentiation and concrete sizing/pagination behavior, which keeps it short of complete.

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 reported at 0%, and the request object is a polymorphic anyOf, so the description carries weight here. It does define the meaning of the query discriminator values and notes that typed filters plus the cursor bind the query, which is genuinely additive. But it never explains the free-text field, the date-range filters, the limit defaults (50 vs 2000 per mode), or cursor vs resultCursor distinction, leaving most parameter semantics to inference from the schema's shape.

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 uses a specific verb ("Search") against a specific resource set ("project message, transcript and summary content") and enumerates the two modes via the query discriminator ("messages", "message_detail"). It does not, however, distinguish this tool from the sibling tools (conversations, knowledge, widgets), so an agent cannot rule out overlap from the text alone.

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 one useful in-tool routing rule: use the "message_detail" query to "Continue one authorized message source" rather than starting a fresh search. There is no guidance on when to call this versus the sibling tools, no prerequisites stated, and no exclusions or failure conditions.

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