Think Tool

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

With no annotations, the description carries the full burden, and it does disclose real behavior: durable cross-session persistence and an auto-generated TEMP session when sessionName is absent. It does not explain what happens to reasoning afterward, how relationships (relates_to/relationship_type) are resolved, or any retention/visibility characteristics.

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?

The purpose leads, followed by a clearly flagged IMPORTANT block and concrete examples, so the most actionable content is front-loaded. There is minor redundancy between the body text and the schema's sessionName description, but no wasted padding.

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 six-parameter tool with no annotations and no output schema, the description covers session handling well but leaves the reasoning-graph side (relates_to and relationship_type enums) and the return behavior unexplained. An agent can call it, but cannot fully predict how thoughts link or what comes back.

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 all six parameters are already documented in the schema, making 3 the baseline. The description reinforces sessionName format and persistence semantics, but adds nothing about mode, tags, relates_to, or relationship_type beyond what the schema already says.

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 frames the tool as 'a persistent thinking workspace that preserves reasoning across sessions,' which conveys the general intent but never states the concrete action (recording/storing a unit of reasoning). Sibling tools (list_sessions, view_session, search_in_session) make clear this is the write side of a session-based store, but the description doesn't explicitly position itself that way.

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 strong guidance on the sessionName parameter (always supply it, use consistent naming for cross-conversation context) and states the fallback when it is omitted. However, it never says when to reach for think versus the sibling retrieval/search tools, so the routing guidance is only implied.

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