memory_search

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

With no annotations, the description carries the full behavioral burden. It does disclose a meaningful trait, that the search spans ALL agent tools' session logs rather than only the current project, and it sketches the return shape (snippets with source and relevance score). It says nothing about permission boundaries, latency, result freshness, or whether empty results are possible.

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 sentences, front-loaded with the scope and immediately followed by usage triggers and the return shape. No filler and no repetition of the schema.

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 3-parameter read tool with no output schema, the description covers purpose, cross-tool scope, invocation triggers, and a one-line return summary. The main gap is behavioral depth that annotations would normally supply, such as ranking, freshness, or failure behavior.

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 query, project, and n_results are already documented with defaults and the 'omit to search everything' behavior. The description adds no syntax, format, or query-construction guidance beyond what the schema provides, so the baseline of 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?

States a specific verb (Search) and resource (shared memory) plus the scope of what is indexed: session logs of this and other AI coding tools, project docs, decisions, notes. That is far more informative than the tool name alone. It does not explicitly contrast itself with memory_write or memory_stats, though the read-vs-write distinction is easy to infer.

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?

"Use it whenever you need past context" is followed by concrete triggers: previous decisions, prior problem-solving, architecture rationale, user preferences. This gives an agent clear conditions for invocation, but offers no exclusions or alternatives (e.g. when to prefer memory_stats for counting, or what to do if the query returns nothing).

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