find_similar_sections

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

Annotations already declare readOnlyHint=true, and the description reinforces with 'Read-only.' It provides algorithmic transparency (fusion logic, clustering method, ranking criteria, verdict tiers) which is genuinely additive. However, it doesn't disclose performance/resource implications (e.g., max_sections=1000 hard cap implications, compute cost, what happens to sections not examined).

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?

Dense, information-rich single paragraph. Front-loaded with the verb-resource pair and algorithm overview. Every sentence adds value — the fusion signals, clustering method, ranking, and output tiers are all meaningful. Slightly dense/compressed but no waste.

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 fairly complex algorithm tool with no output schema, the description covers algorithm, signals, thresholds, and verdict tiers. It doesn't document return format/field details since no output schema exists, and could mention edge-case behavior (e.g., min_score effect on cluster count), but overall adequate for the tool's complexity.

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 67% (4 of 6 params documented in schema). The description adds meaning to the algorithm-level parameters: min_score is a 'pairwise score floor for clustering', thresholds map to verdict tiers semantics. It slightly over-performs baseline 3 by clarifying how the 3 scoring thresholds interrelate with the verdict tiers, but custom outputs are not documented.

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+resource: 'finds similar sections' — but more importantly it precisely defines the multi-signal dedup detection approach (embedding cosine + lexical Jaccard, union-find clustering, canonical ranking). This clearly distinguishes it from sibling tools like get_related_sections and section_neighbors by its clustering/dedup-oriented purpose.

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?

The description implies a dedup/detection use case but does not explicitly state when to use this vs alternatives like get_related_sections or section_neighbors. It lists the verdict tiers (near_duplicate, overlapping_topic, parallel_tutorial) which gives context on output interpretation, but no explicit when-to-use or when-not-to-use guidance.

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