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

With no annotations, the description carries the transparency burden. It discloses the operation sequence (appends to session, compresses history, enriches) and the output shape, which implies the tool transforms context and may write to working memory. It does not state persistence, reversibility, or behavior when neither messages nor prompt is provided.

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?

Three compact sentences with the pipeline summary first, followed by output and usage context. It is efficient, though the arrow-notation pipeline and 'teamsmarted' jargon require the reader to already know the domain.

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?

Given 8 optional parameters, a full output schema, and no annotations, the description supplies the needed usage context and a clear invocation trigger. It could more explicitly distinguish itself from close siblings like context_compress or memory_assemble_context, but the 'before sending a turn' guidance is sufficient for most cases.

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 100%, so the baseline is the correct anchor. The description adds strategic context (why to use it, what it returns) rather than per-parameter explanations; the individual parameters are already well documented in the schema.

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 names a specific pipeline (session append → compress → enrich) and the concrete return payload (messages, optional additional_context, session_id, stats). It also scopes itself against sibling tooling by stating that server-side MCP middleware handles teamshared tool normalization and 'this covers the rest of the prompt.'

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 explicitly says 'Use before sending a turn to your LLM' and gives the condition (want teamshared to shrink tool bloat and inject recall). It does not name an alternative tool explicitly, but the middleware statement provides a boundary against normalization-focused siblings.

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