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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so the safety profile is covered structurally. The description adds real operational context beyond that: first build latency ('can take over an hour on large projects'), the per-project off-by-default behavior, coverage of .ts/.tsx/.js/.jsx/.mjs and skipping of tests/specs/.d.ts, and the 'treat every pair as a candidate' caveat. It does not disclose the result/pair shape, but with an output schema present that is acceptable.

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?

Front-loads the core behavior in the first sentence and then layers usage, prerequisites, and caveats compactly. The dash-separated clauses are dense but each carries actionable information; minor tightening is possible but nothing is 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?

Given five parameters, full schema coverage, an output schema, and annotations, the description supplies the missing operational layer: enabling prerequisite, cost warning, file-type scope, and false-positive caveat. It omits only return-shape details, which the output schema already covers.

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 3. The description goes further by giving a concrete line-range syntax example ('src/a.ts:10-40') and explaining the intent behind line-range inputs (sharper pairs), which the schema does not convey, plus threshold-like tuning guidance ('raise to fewer false pairs').

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 and resource ('List code in other files that nearly matches the given files or line ranges'), and narrows scope to a near-match similarity search rather than general search. It also names the sibling index_project as the enabling mechanism, so an agent can distinguish it from semantic_search.

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?

Explicitly tells the agent when to use it ('in reviews and refactors'), how to sharpen results (pass changed line ranges), when to ask the user before enabling ('ask the user before you turn it on'), and names the prerequisite (index_project duplicates: true). Both when-to-use and gating conditions are covered.

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

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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered structurally. The description adds real behavioral value beyond that: it explains the incremental strategy (only new/edited/outdated files are embedded, deleted ones dropped) and that duplicates indexing is opt-in and persists across calls. It stops short of noting cost/duration or concurrency concerns for a long-running index build.

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 tight sentences: purpose first, then the incremental/destructive behavior, then the one opt-in flag that has side effects on another tool. No filler, and the most decision-relevant fact is front-loaded.

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 4-parameter mutation tool with no output schema and annotations that already carry the safety hints, the description covers purpose, mutation semantics, and the one non-obvious flag. It is complete enough to invoke correctly; only return/status reporting and expected duration are unaddressed, which is minor given index_status exists.

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 path, force, duplicates, and extensions are all self-documenting in the schema. The description reinforces the duplicates parameter's cross-tool effect on find_duplicates, which is mild added meaning, but does not clarify force vs. default or extension-list persistence beyond what the schema says. 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?

States a specific verb+resource ('Build or refresh the semantic index of a project root') and immediately scopes what it touches. It is distinguishable from siblings like index_status (which presumably reports) and semantic_search (which queries) without opening any schema.

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 one concrete usage instruction — pass duplicates: true once to enable find_duplicates — which ties this tool to a sibling. However, it never says when to call this versus index_status (e.g., check status before reindexing) or when a full rebuild (force) is warranted over the default incremental behavior.

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

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), so the description is not obligated to explain that. It does add useful content beyond the annotations by disclosing what the call returns — file, chunk, and size counts per project — which matters given there is no output schema. It stops short of describing freshness, pagination, or behavior for large project sets.

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?

One sentence, front-loaded with the listing behavior and followed immediately by the parameter rule. Nothing is wasted and no sentence is 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 one-parameter read-only tool with no output schema, the description covers the essential elements: what is listed, what is returned, and how the optional path narrows scope. Minor gaps remain around result size/pagination and whether counts reflect a live or stale index.

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 coverage is 100% and the single parameter is already documented as 'Optional project path to check'. The description's 'pass path for one project' reinforces the scoping semantics (omitting it broadens the result set) but adds no format or syntax detail beyond the schema, 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?

The description states a specific verb and resource ('List indexed projects') and even names the returned fields ('file, chunk and size counts'), which is more than a restatement of the title. It does not explicitly distinguish itself from siblings like index_project or find_duplicates, but the read-only listing intent is unambiguous.

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?

'pass path for one project' implies the two modes (omit path to list all, supply path for a single project), so usage is inferable rather than spelled out. There is no explicit when-to-use guidance relative to index_project or the other siblings, so it sits at the implied-usage tier.

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

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

Annotations already declare readOnly, idempotent, and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: results default to file:line references, the caller should then read the files, and only .ts/.tsx are searched unless include adds extensions. Minor gap: nothing about result ordering or the effect of threshold on output volume.

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?

Five short lines, front-loaded with the core purpose, then query style, then return-format and scope defaults. The good/bad examples earn their place by making the query convention unambiguous; there is no filler.

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?

With an output schema present, return values need not be described, and the description still usefully notes the default reference format. It covers query style, default extensions, and the read-the-files follow-up. It is slightly thin on how limit and threshold interact with the returned set.

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 every parameter is already documented, and the baseline is 3. The description largely restates schema content (natural-language sentence, include for extra extensions, file:line default) and adds only the query-phrasing examples; threshold and path receive no additional meaning.

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 and resource — 'Find code by meaning in an indexed project' — and scopes it to an indexed project, which cleanly separates it from the indexing siblings (index_project, index_status) and from find_duplicates. An agent can tell what it retrieves without opening the schema.

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?

Gives concrete invocation guidance: 'Ask one full natural-language sentence, not keywords,' with a good and a bad example, plus the default extension scope and how include extends it. It lacks an explicit when-not-to-use or a direct pointer to a sibling alternative, so it stops short of a 5.

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