save_summary

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

Annotations only declare readOnlyHint=false, so the description carries most of the burden and does add real value by disclosing the side effect that the session gets marked complete. It says nothing about whether repeated calls overwrite the previous summary, whether it is idempotent, or what happens if it is skipped — meaningful gaps for a state-changing tool.

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 short sentences, no waste, with the timing constraint and the side effect both front-loaded. Nothing redundant with the schema or annotations.

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?

It covers the essentials — when to call and what state change results — for a five-parameter write tool with no output schema. However, it leaves open repeat-call semantics and how the saved summary relates to siblings like resume_session or handoff, which an agent would need to call this correctly in edge 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 all five fields (title, accomplished, learned, decisions, next_steps) are already documented with descriptions and length limits. The description adds no guidance on what content belongs in each field or how detailed they should be, so baseline 3 applies.

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?

Specific verb and resource ('Save session summary') plus a stated lifecycle effect ('Marks session as complete'), which separates it from a generic context write. It does not explicitly contrast with siblings like save_context or handoff, so differentiation is implied rather than stated.

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?

'MANDATORY before giving final response' gives an unambiguous trigger condition, and 'at end of work' scopes the timing. No alternatives or exclusions are named, so an agent must infer why it would pick this over save_context.

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